Paper Digest: Recent Papers on Relation Extraction
Paper Digest Team extracted all recent Relation Extraction related papers on our radar, and generated highlight sentences for them. The results are then sorted by relevance & date. In addition to this ‘static’ page, we also provide a real-time version of this article, which has more coverage and is updated in real time to include the most recent updates on this topic.
If you do not want to miss any interesting academic paper, you are welcome to sign up our free daily paper digest service to get updates on new papers published in your area every day. You are also welcome to follow us on Twitter and Linkedin to get updated with new conference digests.
Paper Digest Team
team@paperdigest.org
TABLE 1: Paper Digest: Recent Papers on Relation Extraction
| Paper | Author(s) | Source | Date | |
|---|---|---|---|---|
| 1 | Discourse Relation Embeddings: Representing The Relations Between Discourse Segments in Social Media Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel method for automatically creating discourse relation embeddings (DiscRE), addressing the embedding challenge through a weakly supervised, multitask approach to learn diverse and nuanced relations between discourse segments in social media. |
Youngseo Son; H Andrew Schwartz; | arxiv-cs.CL | 2021-05-04 |
| 2 | An Analysis of Full-size Russian Complexly NER Labelled Corpus of Internet User Reviews on The Drugs Based on Deep Learning and Language Neural Nets Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the full-size Russian complexly NER-labeled corpus of Internet user reviews, along with an evaluation of accuracy levels reached on this corpus by a set of advanced deep learning neural networks to extract the pharmacologically meaningful entities from Russian texts. |
ALEXANDER SBOEV et. al. | arxiv-cs.CL | 2021-04-30 |
| 3 | Multi-view Inference for Relation Extraction with Uncertain Knowledge Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes to exploit uncertain knowledge to improve relation extraction. |
Bo Li; Wei Ye; Canming Huang; Shikun Zhang; | arxiv-cs.CL | 2021-04-28 |
| 4 | Improving BERT Model Using Contrastive Learning for Biomedical Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we explore the method of employing contrastive learning to improve the text representation from the BERT model for relation extraction. |
Peng Su; Yifan Peng; K. Vijay-Shanker; | arxiv-cs.CL | 2021-04-28 |
| 5 | Explore BiLSTM-CRF-Based Models for Open Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we develop several Open RE models based on the bidirectional LSTM-CRF (BiLSTM-CRF) neural network and different contextualized word embedding methods. |
Tao Ni; Qing Wang; Gabriela Ferraro; | arxiv-cs.CL | 2021-04-25 |
| 6 | Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we define a new task in the NLP domain, incremental few-shot text classification, where the system incrementally handles multiple rounds of new classes. In addition to formulating the new task, we also release two benchmark datasets in the incremental few-shot setting: intent classification and relation classification. |
Congying Xia; Wenpeng Yin; Yihao Feng; Philip Yu; | arxiv-cs.CL | 2021-04-24 |
| 7 | Enriched Attention for Robust Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we address this problem with an enriched attention mechanism. |
Heike Adel; Jannik Strötgen; | arxiv-cs.CL | 2021-04-22 |
| 8 | Extracting Adverse Drug Events from Clinical Notes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We explore three approaches: a rule-based approach, a deep learning-based approach, and a contextualized language model-based approach. |
Darshini Mahendran; Bridget T. McInnes; | arxiv-cs.CL | 2021-04-21 |
| 9 | Improving Biomedical Pretrained Language Models with Knowledge Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose KeBioLM, a biomedical pretrained language model that explicitly leverages knowledge from the UMLS knowledge bases. |
Zheng Yuan; Yijia Liu; Chuanqi Tan; Songfang Huang; Fei Huang; | arxiv-cs.CL | 2021-04-20 |
| 10 | Extracting Temporal Event Relation with Syntactic-Guided Temporal Graph Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by the examination of available temporal relation annotations and human-like cognitive procedures, we propose a new Temporal Graph Transformer network to (1) explicitly find the connection between two events from a syntactic graph constructed from one or two continuous sentences, and (2) automatically locate the most indicative temporal cues from the path of the two event mentions as well as their surrounding concepts in the syntactic graph with a new temporal-oriented attention mechanism. |
Shuaicheng Zhang; Lifu Huang; Qiang Ning; | arxiv-cs.CL | 2021-04-19 |
| 11 | Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To remedy this, we propose a novel methodology for deriving more realistic few-shot test data from available datasets for supervised RC, and apply it to the TACRED dataset. |
Ofer Sabo; Yanai Elazar; Yoav Goldberg; Ido Dagan; | arxiv-cs.CL | 2021-04-17 |
| 12 | DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In response, we propose a new dataset, DiS-ReX, which alleviates these issues. |
Abhyuday Bhartiya; Kartikeya Badola; Mausam; | arxiv-cs.CL | 2021-04-17 |
| 13 | Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a multi-task, probabilistic approach to facilitate distantly supervised relation extraction by bringing closer the representations of sentences that contain the same Knowledge Base pairs. |
Fenia Christopoulou; Makoto Miwa; Sophia Ananiadou; | arxiv-cs.CL | 2021-04-16 |
| 14 | Re-TACRED: Addressing Shortcomings of The TACRED Dataset Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we address these shortcomings by: (i) performing a comprehensive study over the whole TACRED dataset, (ii) proposing an improved crowdsourcing strategy and deploying it to re-annotate the whole dataset, and (iii) performing a thorough analysis to understand how correcting the TACRED annotations affects previously published results. |
George Stoica; Emmanouil Antonios Platanios; Barnabás Póczos; | arxiv-cs.CL | 2021-04-16 |
| 15 | A Sample-Based Training Method for Distantly Supervised Relation Extraction with Pre-Trained Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel sampling method for DSRE that relaxes these hardware requirements. |
Mehrdad Nasser; Mohamad Bagher Sajadi; Behrouz Minaei-Bidgoli; | arxiv-cs.CL | 2021-04-15 |
| 16 | AdaPrompt: Adaptive Prompt-based Finetuning for Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we reformulate the relation extraction task as mask language modeling and propose a novel adaptive prompt-based finetuning approach. |
XIANG CHEN et. al. | arxiv-cs.CL | 2021-04-15 |
| 17 | ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formulate the zero-shot relation extraction problem by incorporating the text description of seen and unseen relations. |
Chih-Yao Chen; Cheng-Te Li; | arxiv-cs.CL | 2021-04-10 |
| 18 | UPB at SemEval-2021 Task 8: Extracting Semantic Information on Measurements As Multi-Turn Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We approached these challenges by first identifying the quantities, extracting their units of measurement, classifying them with corresponding modifiers, and afterwards using them to jointly solve the last three subtasks in a multi-turn question answering manner. |
Andrei-Marius Avram; George-Eduard Zaharia; Dumitru-Clementin Cercel; Mihai Dascalu; | arxiv-cs.CL | 2021-04-09 |
| 19 | A Question-answering Based Framework for Relation Extraction Validation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore the possibility of using question answering as validation. |
Jiayang Cheng; Haiyun Jiang; Deqing Yang; Yanghua Xiao; | arxiv-cs.CL | 2021-04-07 |
| 20 | Deep Neural Networks for Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Relation extraction from text is an important task for automatic knowledge base population. In this thesis, we first propose a syntax-focused multi-factor attention network model … |
Tapas Nayak; | arxiv-cs.CL | 2021-04-05 |
| 21 | Counts@IITK at SemEval-2021 Task 8: SciBERT Based Entity And Semantic Relation Extraction For Scientific Data Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the system for SemEval 2021 Task 8 (MeasEval). |
Akash Gangwar; Sabhay Jain; Shubham Sourav; Ashutosh Modi; | arxiv-cs.CL | 2021-04-03 |
| 22 | Normal Vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we take the first step to leverage the salience-based method to analyze those adversarial samples. |
LUOQIU LI et. al. | arxiv-cs.CL | 2021-04-01 |
| 23 | Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To help future research, we present a comprehensive review of the recently published research works in relation extraction. |
Tapas Nayak; Navonil Majumder; Pawan Goyal; Soujanya Poria; | arxiv-cs.CL | 2021-03-31 |
| 24 | Multi-facet Universal Schema Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the violation of the USchema assumption, we propose multi-facet universal schema that uses a neural model to represent each sentence pattern as multiple facet embeddings and encourage one of these facet embeddings to be close to that of another sentence pattern if they co-occur with the same entity pair. |
Rohan Paul; Haw-Shiuan Chang; Andrew McCallum; | arxiv-cs.CL | 2021-03-29 |
| 25 | Prototypical Representation Learning for Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead of solely relying on the supervision from noisy labels, we propose to learn prototypes for each relation from contextual information to best explore the intrinsic semantics of relations. |
NING DING et. al. | arxiv-cs.CL | 2021-03-22 |
| 26 | Structural Block Driven – Enhanced Convolutional Neural Representation for Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel lightweight relation extraction approach of structural block driven – convolutional neural learning. |
Dongsheng Wang; Prayag Tiwari; Sahil Garg; Hongyin Zhu; Peter Bruza; | arxiv-cs.CL | 2021-03-21 |
| 27 | Leveraging Unlabeled Data for Entity-Relation Extraction Through Probabilistic Constraint Satisfaction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We study the problem of entity-relation extraction in the presence of symbolic domain knowledge. |
Kareem Ahmed; Eric Wang; Guy Van den Broeck; Kai-Wei Chang; | arxiv-cs.LG | 2021-03-19 |
| 28 | Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a novel deep learning model to simultaneously solve the four tasks of IE in a single model (called FourIE). |
Minh Van Nguyen; Viet Dac Lai; Thien Huu Nguyen; | arxiv-cs.CL | 2021-03-16 |
| 29 | Mention-centered Graph Neural Network for Document-level Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we build cross-sentence dependencies by inferring compositional relations between inter-sentence mentions. |
Jiaxin Pan; Min Peng; Yiyan Zhang; | arxiv-cs.CL | 2021-03-15 |
| 30 | Bidirectional Machine Reading Comprehension for Aspect Sentiment Triplet Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we transform ASTE task into a multi-turn machine reading comprehension (MTMRC) task and propose a bidirectional MRC (BMRC) framework to address this challenge. |
Shaowei Chen; Yu Wang; Jie Liu; Yuelin Wang; | arxiv-cs.CL | 2021-03-13 |
| 31 | A Review on Semi-Supervised Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we review and compare three typical methods in semi-supervised RE with deep learning or meta-learning: self-ensembling, which forces consistent under perturbations but may confront insufficient supervision; self-training, which iteratively generates pseudo labels and retrain itself with the enlarged labeled set; dual learning, which leverages a primal task and a dual task to give mutual feedback. |
Yusen Lin; | arxiv-cs.CL | 2021-03-12 |
| 32 | Techniques for Jointly Extracting Entities and Relations: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we survey various techniques for jointly extracting entities and relations. |
Sachin Pawar; Pushpak Bhattacharyya; Girish K. Palshikar; | arxiv-cs.CL | 2021-03-10 |
| 33 | Dual Pointer Network for Fast Extraction of Multiple Relations in A Sentence IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a relation extraction model based on a dual pointer network with a multi-head attention mechanism. |
Seongsik Park; Harksoo Kim; | arxiv-cs.CL | 2021-03-05 |
| 34 | Better Call The Plumber: Orchestrating Dynamic Information Extraction Pipelines Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose Plumber, the first framework that brings together the research community’s disjoint IE efforts. |
Mohamad Yaser Jaradeh; Kuldeep Singh; Markus Stocker; Andreas Both; Sören Auer; | arxiv-cs.CL | 2021-02-22 |
| 35 | REMOD: Relation Extraction for Modeling Online Discourse Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here we develop a novel supervised learning method for relation extraction that combines graph embedding techniques with path traversal on semantic dependency graphs. |
Matthew Sumpter; Giovanni Luca Ciampaglia; | arxiv-cs.SI | 2021-02-22 |
| 36 | Contextual Argument Component Classification for Class Discussions IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we show how two different types of contextual information, local discourse context and speaker context, can be incorporated into a computational model for classifying argument components in multi-party classroom discussions. |
Luca Lugini; Diane Litman; | arxiv-cs.CL | 2021-02-20 |
| 37 | Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we formulate such structure as distinctive dependencies between mention pairs. |
Benfeng Xu; Quan Wang; Yajuan Lyu; Yong Zhu; Zhendong Mao; | arxiv-cs.CL | 2021-02-19 |
| 38 | WebRED: Effective Pretraining And Finetuning For Relation Extraction On The Web Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We therefore introduce: WebRED (Web Relation Extraction Dataset), a strongly-supervised human annotated dataset for extracting relationships from a variety of text found on the World Wide Web, consisting of ~110K examples. |
Robert Ormandi; Mohammad Saleh; Erin Winter; Vinay Rao; | arxiv-cs.CL | 2021-02-18 |
| 39 | Decoding EEG Brain Activity for Multi-Modal Natural Language Processing Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present the first large-scale study of systematically analyzing the potential of EEG brain activity data for improving natural language processing tasks, with a special focus on which features of the signal are most beneficial. |
NORA HOLLENSTEIN et. al. | arxiv-cs.CL | 2021-02-17 |
| 40 | Two Training Strategies for Improving Relation Extraction Over Universal Graph Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The code and datasets used in this paper are available at https://github.com/baodaiqin/UGDSRE. |
Qin Dai; Naoya Inoue; Ryo Takahashi; Kentaro Inui; | arxiv-cs.CL | 2021-02-12 |
| 41 | An End-to-end Model for Entity-level Relation Extraction Using Multi-instance Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a joint model for entity-level relation extraction from documents. |
Markus Eberts; Adrian Ulges; | arxiv-cs.CL | 2021-02-11 |
| 42 | Information Prediction Using Knowledge Graphs for Contextual Malware Threat Intelligence Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes an end-to-end approach to generate a Malware Knowledge Graph called MalKG, the first open-source automated knowledge graph for malware threat intelligence. |
NIDHI RASTOGI et. al. | arxiv-cs.CR | 2021-02-10 |
| 43 | Bootstrapping Relation Extractors Using Syntactic Search By Examples Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we propose a process for bootstrapping training datasets which can be performed quickly by non-NLP-experts. |
Matan Eyal; Asaf Amrami; Hillel Taub-Tabib; Yoav Goldberg; | arxiv-cs.CL | 2021-02-09 |
| 44 | Memorization Vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We identify leakage of training data into test data on several publicly available datasets used to evaluate NLP tasks, including named entity recognition and relation extraction, and study them to assess the impact of that leakage on the model’s ability to memorize versus generalize. |
Aparna Elangovan; Jiayuan He; Karin Verspoor; | arxiv-cs.CL | 2021-02-02 |
| 45 | An Improved Baseline for Sentence-level Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this report, we revisit two problems that affect the performance of existing RE models, namely entity representation and noisy or ill-defined labels. |
Wenxuan Zhou; Muhao Chen; | arxiv-cs.CL | 2021-02-02 |
| 46 | Neural Data Augmentation Via Example Extrapolation Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a data augmentation approach that performs neural Example Extrapolation (Ex2). |
Kenton Lee; Kelvin Guu; Luheng He; Tim Dozat; Hyung Won Chung; | arxiv-cs.CL | 2021-02-02 |
| 47 | Improving Distantly-Supervised Relation Extraction Through BERT-based Label & Instance Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose REDSandT (Relation Extraction with Distant Supervision and Transformers), a novel distantly-supervised transformer-based RE method, that manages to capture a wider set of relations through highly informative instance and label embeddings for RE, by exploiting BERT’s pre-trained model, and the relationship between labels and entities, respectively. |
Despina Christou; Grigorios Tsoumakas; | arxiv-cs.CL | 2021-02-01 |
| 48 | Is Depression Related to Cannabis?: A Knowledge-infused Model for Entity and Relation Extraction with Limited Supervision Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we explore the relationship between depression and consumption of cannabis in a targeted social media corpus involving personal use of cannabis with the intent to derive its potential mental health benefit. |
Kaushik Roy; Usha Lokala; Vedant Khandelwal; Amit Sheth; | arxiv-cs.CL | 2021-02-01 |
| 49 | LOME: Large Ontology Multilingual Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present LOME, a system for performing multilingual information extraction. |
PATRICK XIA et. al. | arxiv-cs.CL | 2021-01-28 |
| 50 | Enquire One’s Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the Hierarchy Expansion Framework (HEF), which fully exploits the hierarchical structure’s properties to maximize the coherence of expanded taxonomy. |
Suyuchen Wang; Ruihui Zhao; Xi Chen; Yefeng Zheng; Bang Liu; | arxiv-cs.CL | 2021-01-27 |
| 51 | Laughing at You Or with You: The Role of Sarcasm in Shaping The Disagreement Space IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To further our understanding of the role of sarcasm in shaping the disagreement space, we present a thorough experimental setup using a corpus annotated with both argumentative moves (agree/disagree) and sarcasm. |
Debanjan Ghosh; Ritvik Shrivastava; Smaranda Muresan; | arxiv-cs.CL | 2021-01-26 |
| 52 | Process-Level Representation of Scientific Protocols with Interactive Annotation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We develop Process Execution Graphs (PEG), a document-level representation of real-world wet lab biochemistry protocols, addressing challenges such as cross-sentence relations, long-range coreference, grounding, and implicit arguments. |
Ronen Tamari; Fan Bai; Alan Ritter; Gabriel Stanovsky; | arxiv-cs.CL | 2021-01-25 |
| 53 | A Trigger-Sense Memory Flow Framework for Joint Entity and Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we present a Trigger-Sense Memory Flow Framework (TriMF) for joint entity and relation extraction. |
Yongliang Shen; Xinyin Ma; Yechun Tang; Weiming Lu; | arxiv-cs.CL | 2021-01-25 |
| 54 | Video Relation Detection with Trajectory-aware Multi-modal Features IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present video relation detection with trajectory-aware multi-modal features to solve this task. |
Wentao Xie; Guanghui Ren; Si Liu; | arxiv-cs.CV | 2021-01-20 |
| 55 | HIVE-4-MAT: Advancing The Ontology Infrastructure for Materials Science IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Introduces HIVE-4-MAT – Helping Interdisciplinary Vocabulary Engineering for Materials Science, an automatic linked data ontology application. Covers contextual background for … |
Jane Greenberg; Xintong Zhao; Joseph Adair; Joan Boone; Xiaohua Tony Hu; | arxiv-cs.DL | 2021-01-19 |
| 56 | A Survey on Extraction of Causal Relations from Natural Language Text IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we conduct a comprehensive survey of causality extraction. |
Jie Yang; Soyeon Caren Han; Josiah Poon; | arxiv-cs.IR | 2021-01-16 |
| 57 | Structured Prediction As Translation Between Augmented Natural Languages IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new framework, Translation between Augmented Natural Languages (TANL), to solve many structured prediction language tasks including joint entity and relation extraction, nested named entity recognition, relation classification, semantic role labeling, event extraction, coreference resolution, and dialogue state tracking. |
GIOVANNI PAOLINI et. al. | arxiv-cs.LG | 2021-01-14 |
| 58 | EventPlus: A Temporal Event Understanding Pipeline IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present EventPlus, a temporal event understanding pipeline that integrates various state-of-the-art event understanding components including event trigger and type detection, event argument detection, event duration and temporal relation extraction. |
MINGYU DEREK MA et. al. | arxiv-cs.CL | 2021-01-13 |
| 59 | Predicting Relative Depth Between Objects from Semantic Features IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper the extent to which semantic features can predict course relative depth is investigated. |
Stefan Cassar; Adrian Muscat; Dylan Seychell; | arxiv-cs.CV | 2021-01-12 |
| 60 | BERT-GT: Cross-sentence N-ary Relation Extraction with BERT and Graph Transformer IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel architecture that combines Bidirectional Encoder Representations from Transformers with Graph Transformer (BERT-GT), through integrating a neighbor-attention mechanism into the BERT architecture. |
Po-Ting Lai; Zhiyong Lu; | arxiv-cs.CL | 2021-01-11 |
| 61 | Adaptive Prototypical Networks with Label Words and Joint Representation Learning for Few-Shot Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To make full use of the existing information and get a better feature representation for each instance, we propose to encode each class prototype in an adaptive way from two aspects. |
Yan Xiao; Yaochu Jin; Kuangrong Hao; | arxiv-cs.CL | 2021-01-10 |
| 62 | Learning Better Sentence Representation with Syntax Information IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel approach to combining syntax information with a pre-trained language model. |
Chen Yang; | arxiv-cs.CL | 2021-01-09 |
| 63 | Curriculum-Meta Learning for Order-Robust Continual Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel curriculum-meta learning method to tackle the above two challenges in continual relation extraction. |
TONGTONG WU et. al. | arxiv-cs.CL | 2021-01-06 |
| 64 | Deep Neural Network Based Relation Extraction: An Overview IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This article 1) introduces some general concepts, and further 2) gives a comprehensive overview of DNNs in RE from two points of view: supervised RE, which attempts to improve the standard RE systems, and distant supervision RE, which adopts DNNs to design sentence encoder and de-noise method. |
Hailin Wang; Ke Qin; Rufai Yusuf Zakari; Guoming Lu; Jin Yin; | arxiv-cs.CL | 2021-01-06 |
| 65 | MrGCN: Mirror Graph Convolution Network For Relation Extraction With Long-Term Dependencies IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we leverage the idea of graph pooling and propose the Mirror Graph Convolution Network (MrGCN), a GNN model with pooling-unpooling structures tailored to relation extraction. |
Xiao Guo; I-Hung Hsu; Wael AbdAlmageed; Premkumar Natarajan; Nanyun Peng; | arxiv-cs.CL | 2020-12-31 |
| 66 | Syntax-Enhanced Pre-trained Model IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. |
ZENAN XU et. al. | arxiv-cs.CL | 2020-12-28 |
| 67 | An Embarrassingly Simple Model For Dialogue Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we model Dialogue RE as a multi-label classification task and propose a simple yet effective model named SimpleRE. |
Fuzhao Xue; Aixin Sun; Hao Zhang; Eng Siong Chng; | arxiv-cs.CL | 2020-12-27 |
| 68 | Document-Level Relation Extraction With Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this issue, we propose a novel encoder-classifier-reconstructor model for DocRE. |
Wang Xu; Kehai Chen; Tiejun Zhao; | arxiv-cs.CL | 2020-12-21 |
| 69 | Towards Incorporating Entity-specific Knowledge Graph Information In Predicting Drug-Drug Interactions Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore how to incorporate domain knowledge of the biomedical entities (such as drug, disease, genes), obtained from Knowledge Graph (KG) Embeddings, for predicting Drug-Drug Interaction from textual corpus. |
Ishani Mondal; | arxiv-cs.CL | 2020-12-21 |
| 70 | A Hybrid Deep-learning Approach For Complex Biochemical Named Entity Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a hybrid deep learning approach to improve the recognition accuracy of NER. |
JIAN LIU et. al. | arxiv-cs.CL | 2020-12-19 |
| 71 | An Empirical Study of Using Pre-trained BERT Models for Vietnamese Relation Extraction Task at VLSP 2020 IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an empirical study of using pre-trained BERT models for the relation extraction task at the VLSP 2020 Evaluation Campaign. |
Pham Quang Nhat Minh; | arxiv-cs.CL | 2020-12-18 |
| 72 | Regularized Attentive Capsule Network For Overlapped Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a novel Regularized Attentive Capsule Network (RA-CapNet) to better identify highly overlapped relations in each informal sentence. |
Tianyi Liu; Xiangyu Lin; Weijia Jia; Mingliang Zhou; Wei Zhao; | arxiv-cs.CL | 2020-12-18 |
| 73 | Clinical Temporal Relation Extraction With Probabilistic Soft Logic Regularization And Global Inference IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel method, Clinical Temporal ReLation Exaction with Probabilistic Soft Logic Regularization and Global Inference (CTRL-PG) to tackle the problem at the document level. |
YICHAO ZHOU et. al. | arxiv-cs.CL | 2020-12-16 |
| 74 | InSRL: A Multi-view Learning Framework Fusing Multiple Information Sources For Distantly-supervised Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce two widely-existing sources in knowledge bases, namely entity descriptions, and multi-grained entity types to enrich the distantly supervised data. |
Zhendong Chu; Haiyun Jiang; Yanghua Xiao; Wei Wang; | arxiv-cs.CL | 2020-12-16 |
| 75 | R$^2$-Net: Relation Of Relation Learning Network For Sentence Semantic Matching Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose a Relation of Relation Learning Network (R2-Net) for sentence semantic matching. |
KUN ZHANG et. al. | arxiv-cs.CL | 2020-12-16 |
| 76 | GDPNet: Refining Latent Multi-View Graph For Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to construct a latent multi-view graph to capture various possible relationships among tokens. |
Fuzhao Xue; Aixin Sun; Hao Zhang; Eng Siong Chng; | arxiv-cs.CL | 2020-12-12 |
| 77 | Complex Relation Extraction: Challenges And Opportunities IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Then we summarize the existing complex relation extraction tasks and present the definition, recent progress, challenges and opportunities for each task. |
HAIYUN JIANG et. al. | arxiv-cs.CL | 2020-12-08 |
| 78 | Improving Relation Extraction By Leveraging Knowledge Graph Link Prediction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we leverage this insight by proposing a multi-task learning approach that improves the performance of RE models by jointly training on RE and KGLP tasks. |
George Stoica; Emmanouil Antonios Platanios; Barnabás Póczos; | arxiv-cs.CL | 2020-12-08 |
| 79 | From Bag Of Sentences To Document: Distantly Supervised Relation Extraction Via Machine Reading Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new DS paradigm–document-based distant supervision, which models relation extraction as a document-based machine reading comprehension (MRC) task. |
Lingyong Yan; Xianpei Han; Le Sun; Fangchao Liu; Ning Bian; | arxiv-cs.CL | 2020-12-08 |
| 80 | H-FND: Hierarchical False-Negative Denoising For Distant Supervision Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We here propose H-FND, a hierarchical false-negative denoising framework for robust distant supervision relation extraction, as an FN denoising solution. |
Jhih-Wei Chen; Tsu-Jui Fu; Chen-Kang Lee; Wei-Yun Ma; | arxiv-cs.CL | 2020-12-07 |
| 81 | Financial Document Causality Detection Shared Task (FinCausal 2020) IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the FinCausal 2020 Shared Task on Causality Detection in Financial Documents and the associated FinCausal dataset, and discuss the participating systems and results. |
DOMINIQUE MARIKO et. al. | arxiv-cs.CL | 2020-12-04 |
| 82 | Coarse-to-Fine Entity Representations For Document-level Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Therefore, to obtain more comprehensive entity representations, we propose the \textbf{C}oarse-to-\textbf{F}ine \textbf{E}ntity \textbf{R}epresentation model (\textbf{CFER}) that adopts a coarse-to-fine strategy involving two phases. |
Damai Dai; Jing Ren; Shuang Zeng; Baobao Chang; Zhifang Sui; | arxiv-cs.CL | 2020-12-04 |
| 83 | DDRel: A New Dataset For Interpersonal Relation Classification In Dyadic Dialogues IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose the task of relation classification of interlocutors based on their dialogues. |
Qi Jia; Hongru Huang; Kenny Q. Zhu; | arxiv-cs.CL | 2020-12-04 |
| 84 | Event Guided Denoising For Multilingual Relation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a methodology for collecting high quality training data for relation extraction from unlabeled text that achieves a near-recreation of their zero-shot and few-shot results at a fraction of the training cost. |
Amith Ananthram; Emily Allaway; Kathleen McKeown; | arxiv-cs.CL | 2020-12-04 |
| 85 | Rel3D: A Minimally Contrastive Benchmark For Grounding Spatial Relations In 3D IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we fill this gap by constructing Rel3D: the first large-scale, human-annotated dataset for grounding spatial relations in 3D. |
Ankit Goyal; Kaiyu Yang; Dawei Yang; Jia Deng; | arxiv-cs.CV | 2020-12-02 |
| 86 | Automatic Extraction Of Ranked SNP-Phenotype Associations From Literature Through Detecting Neural Candidates, Negation And Modality Markers IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, first a relation extraction method relying on linguistic-based negation detection and neutral candidates is proposed. |
Behrouz Bokharaeian; Alberto Diaz; | arxiv-cs.CL | 2020-12-01 |
| 87 | Learning Relation Prototype From Unlabeled Texts For Long-tail Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a general approach to learn relation prototypesfrom unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient trainingdata. |
YIXIN CAO et. al. | arxiv-cs.CL | 2020-11-27 |
| 88 | Joint Extraction Of Entity And Relation With Information Redundancy Elimination IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve the problem of redundant information and overlapping relations of the entity and relation extraction model, we propose a joint extraction model. |
Yuanhao Shen; Jungang Han; | arxiv-cs.CL | 2020-11-27 |
| 89 | Experiments On Transfer Learning Architectures For Biomedical Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we explore various BERT-based architectures and transfer learning strategies (i.e., frozen or fine-tuned) for the task of biomedical RE on two corpora. |
Walid Hafiane; Joel Legrand; Yannick Toussaint; Adrien Coulet; | arxiv-cs.CL | 2020-11-24 |
| 90 | RTFN: A Robust Temporal Feature Network For Time Series Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we propose a novel robust temporal feature network (RTFN) for feature extraction in time series classification, containing a temporal feature network (TFN) and an LSTM-based attention network (LSTMaN). |
ZHIWEN XIAO et. al. | arxiv-cs.LG | 2020-11-23 |
| 91 | Dual Supervision Framework For Relation Extraction With Distant Supervision And Human Annotation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To take advantage of the high accuracy of human annotation and the cheap cost of distant supervision, we propose the dual supervision framework which effectively utilizes both types of data. |
Woohwan Jung; Kyuseok Shim; | arxiv-cs.CL | 2020-11-23 |
| 92 | Learning Informative Representations Of Biomedical Relations With Latent Variable Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a latent variable model with an arbitrarily flexible distribution to represent the relation between an entity pair. |
Harshil Shah; Julien Fauqueur; | arxiv-cs.CL | 2020-11-20 |
| 93 | Relation Extraction With Contextualized Relation Embedding (CRE) IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes an architecture for the relation extraction task that integrates semantic information with knowledge base modeling in a novel manner. |
Xiaoyu Chen; Rohan Badlani; | arxiv-cs.CL | 2020-11-19 |
| 94 | Entity Recognition And Relation Extraction From Scientific And Technical Texts In Russian IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, several modifications of methods for the Russian language are proposed. In this paper, we present a corpus of scientific texts in Russian, RuSERRC. |
Elena Bruches; Alexey Pauls; Tatiana Batura; Vladimir Isachenko; | arxiv-cs.CL | 2020-11-19 |
| 95 | Zero-shot Learning For Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a zero-shot learning relation extraction (ZSLRE) framework, which focuses on recognizing novel relations that have no corresponding labeled data available for training. |
Jiaying Gong; Hoda Eldardiry; | arxiv-cs.CL | 2020-11-13 |
| 96 | LUKE: Deep Contextualized Entity Representations With Entity-aware Self-attention IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. |
Ikuya Yamada; Akari Asai; Hiroyuki Shindo; Hideaki Takeda; Yuji Matsumoto; | emnlp | 2020-11-12 |
| 97 | FedED: Federated Learning Via Ensemble Distillation For Medical Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a privacy-preserving medical relation extraction model based on federated learning, which enables training a central model with no single piece of private local data being shared or exchanged. |
DIANBO SUI et. al. | emnlp | 2020-11-12 |
| 98 | Global-to-Local Neural Networks For Document-Level Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel model to document-level RE, by encoding the document information in terms of entity global and local representations as well as context relation representations. |
Difeng Wang; Wei Hu; Ermei Cao; Weijian Sun; | emnlp | 2020-11-12 |
| 99 | Double Graph Based Reasoning For Document-level Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose Graph Aggregation-and-Inference Network (GAIN), a method to recognize such relations for long paragraphs. |
Shuang Zeng; Runxin Xu; Baobao Chang; Lei Li; | emnlp | 2020-11-12 |
| 100 | Domain Knowledge Empowered Structured Neural Net For End-to-End Event Temporal Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, we propose a framework that enhances deep neural network with distributional constraints constructed by probabilistic domain knowledge. |
Rujun Han; Yichao Zhou; Nanyun Peng; | emnlp | 2020-11-12 |
| 101 | Recurrent Interaction Network For Jointly Extracting Entities And Classifying Relations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: As a solution, we design a multi-task learning model which we refer to as recurrent interaction network which allows the learning of interactions dynamically, to effectively model task-specific features for classification. |
Kai Sun; Richong Zhang; Samuel Mensah; Yongyi Mao; Xudong Liu; | emnlp | 2020-11-12 |
| 102 | An Empirical Study Of Pre-trained Transformers For Arabic Information Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we pre-train a customized bilingual BERT, dubbed GigaBERT, that is designed specifically for Arabic NLP and English-to-Arabic zero-shot transfer learning. |
Wuwei Lan; Yang Chen; Wei Xu; Alan Ritter; | emnlp | 2020-11-12 |
| 103 | Biomedical Named Entity Recognition At Scale IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Reimplementing a Bi-LSTM-CNN-Char deep learning architecture on top of Apache Spark, we present a single trainable NER model that obtains new state-of-the-art results on seven public biomedical benchmarks without using heavy contextual embeddings like BERT. |
Veysel Kocaman; David Talby; | arxiv-cs.CL | 2020-11-12 |
| 104 | Pre-training Entity Relation Encoder With Intra-span And Inter-span Information IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we integrate span-related information into pre-trained encoder for entity relation extraction task. |
YIJUN WANG et. al. | emnlp | 2020-11-12 |
| 105 | Exposing Shallow Heuristics Of Relation Extraction Models With Challenge Data IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We identify failure modes of SOTA relation extraction (RE) models trained on TACRED, which we attribute to limitations in the data annotation process. |
Shachar Rosenman; Alon Jacovi; Yoav Goldberg; | emnlp | 2020-11-12 |
| 106 | SelfORE: Self-supervised Relational Feature Learning For Open Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a self-supervised framework named SelfORE, which exploits weak, self-supervised signals by leveraging large pretrained language model for adaptive clustering on contextualized relational features, and bootstraps the self-supervised signals by improving contextualized features in relation classification. |
Xuming Hu; Lijie Wen; Yusong Xu; Chenwei Zhang; Philip Yu; | emnlp | 2020-11-12 |
| 107 | APE: Argument Pair Extraction From Peer Review And Rebuttal Via Multi-task Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new argument pair extraction (APE) task on peer review and rebuttal in order to study the contents, the structure and the connections between them. |
Liying Cheng; Lidong Bing; Qian Yu; Wei Lu; Luo Si; | emnlp | 2020-11-12 |
| 108 | Two Are Better Than One: Joint Entity And Relation Extraction With Table-Sequence Encoders IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose the novel table-sequence encoders where two different encoders – a table encoder and a sequence encoder are designed to help each other in the representation learning process. |
Jue Wang; Wei Lu; | emnlp | 2020-11-12 |
| 109 | BioMegatron: Larger Biomedical Domain Language Model IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We empirically study and evaluate several factors that can affect performance on domain language applications, such as the sub-word vocabulary set, model size, pre-training corpus, and domain transfer. |
HOO-CHANG SHIN et. al. | emnlp | 2020-11-12 |
| 110 | An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we conduct an empirical investigation into known methods to mitigate CF. |
Kristjan Arumae; Qing Sun; Parminder Bhatia; | emnlp | 2020-11-12 |
| 111 | Within-Between Lexical Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the novel \textit{Within-Between} Relation model for recognizing lexical-semantic relations between words. |
Oren Barkan; Avi Caciularu; Ido Dagan; | emnlp | 2020-11-12 |
| 112 | AutoPrompt: Eliciting Knowledge From Language Models With Automatically Generated Prompts IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we develop AutoPrompt, an automated method to create prompts for a diverse set of tasks, based on a gradient-guided search. |
Taylor Shin; Yasaman Razeghi; Robert L. Logan IV; Eric Wallace; Sameer Singh; | emnlp | 2020-11-12 |
| 113 | Denoising Relation Extraction From Document-level Distant Supervision IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate this issue, we propose a novel pre-trained model for DocRE, which de-emphasize noisy DS data via multiple pre-training tasks. |
CHAOJUN XIAO et. al. | emnlp | 2020-11-12 |
| 114 | Let’s Stop Incorrect Comparisons In End-to-end Relation Extraction! Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we first identify several patterns of invalid comparisons in published papers and describe them to avoid their propagation. We then propose a small empirical study to quantify the most common mistake’s impact and evaluate it leads to overestimating the final RE performance by around 5% on ACE05. |
Bruno Taillé; Vincent Guigue; Geoffrey Scoutheeten; Patrick Gallinari; | emnlp | 2020-11-12 |
| 115 | Biomedical Information Extraction For Disease Gene Prioritization IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a biomedical information extraction (IE) pipeline that extracts biological relationships from text and demonstrate that its components, such as named entity recognition (NER) and relation extraction (RE), outperform state-of-the-art in BioNLP. |
Jupinder Parmar; William Koehler; Martin Bringmann; Katharina Sophia Volz; Berk Kapicioglu; | arxiv-cs.LG | 2020-11-10 |
| 116 | Unsupervised Relation Extraction From Language Models Using Constrained Cloze Completion IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce RE-Flex, a simple framework that performs constrained cloze completion over pretrained language models to perform unsupervised relation extraction. |
Ankur Goswami; Akshata Bhat; Hadar Ohana; Theodoros Rekatsinas; | emnlp | 2020-11-10 |
| 117 | E-BERT: Efficient-Yet-Effective Entity Embeddings For BERT IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel way of injecting factual knowledge about entities into the pretrained BERT model (Devlin et al., 2019): We align Wikipedia2Vec entity vectors (Yamada et al., 2016) with BERT’s native wordpiece vector space and use the aligned entity vectors as if they were wordpiece vectors. |
Nina Poerner; Ulli Waltinger; Hinrich Schütze; | emnlp | 2020-11-10 |
| 118 | The Dots Have Their Values: Exploiting The Node-Edge Connections In Graph-based Neural Models For Document-level Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose to explicitly compute the representations for the nodes in the graph-based edge-oriented model for DRE. |
Hieu Minh Tran; Minh Trung Nguyen; Thien Huu Nguyen; | emnlp | 2020-11-10 |
| 119 | Minimize Exposure Bias Of Seq2Seq Models In Joint Entity And Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel Sequence-to-Unordered-Multi-Tree (Seq2UMTree) model to minimize the effects of exposure bias by limiting the decoding length to three within a triplet and removing the order among triplets. |
RANRAN HAORAN ZHANG et. al. | emnlp | 2020-11-10 |
| 120 | Active Testing: An Unbiased Evaluation Method For Distantly Supervised Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate this problem, we propose a novel evaluation method named active testing through utilizing both the noisy test set and a few manual annotations. |
Pengshuai Li; Xinsong Zhang; Weijia Jia; Wei Zhao; | emnlp | 2020-11-10 |
| 121 | Dynamically Updating Event Representations For Temporal Relation Classification With Multi-category Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents an event centric model that allows to manage dynamic event representations across multiple TLINKs. |
Fei Cheng; Masayuki Asahara; Ichiro Kobayashi; Sadao Kurohashi; | emnlp | 2020-11-10 |
| 122 | The RELX Dataset And Matching The Multilingual Blanks For Cross-lingual Relation Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For evaluation, we introduce a new public benchmark dataset for cross-lingual relation classification in English, French, German, Spanish, and Turkish, called RELX. |
Abdullatif Köksal; Arzucan Özgür; | emnlp | 2020-11-10 |
| 123 | CODER: Knowledge Infused Cross-lingual Medical Term Embedding For Term Normalization IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel medical term embedding method named CODER, which stands for mediCal knOwledge embeDded tErm Representation. |
Zheng Yuan; Zhengyun Zhao; Sheng Yu; | arxiv-cs.CL | 2020-11-05 |
| 124 | Joint Entity And Relation Extraction With Set Prediction Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this set prediction problem, we propose networks featured by transformers with non-autoregressive parallel decoding. |
DIANBO SUI et. al. | arxiv-cs.CL | 2020-11-03 |
| 125 | Investigation Of BERT Model On Biomedical Relation Extraction Based On Revised Fine-tuning Mechanism IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we will investigate the method of utilizing the entire layer in the fine-tuning process of BERT model. |
Peng Su; K. Vijay-Shanker; | arxiv-cs.CL | 2020-10-31 |
| 126 | A Sui Generis QA Approach Using RoBERTa For Adverse Drug Event Identification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a question answering framework that exploits the robustness, masking and dynamic attention capabilities of RoBERTa by a technique of domain adaptation and attempt to overcome the aforementioned limitations. |
Harshit Jain; Nishant Raj; Suyash Mishra; | arxiv-cs.CL | 2020-10-30 |
| 127 | Logic-guided Semantic Representation Learning For Zero-Shot Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel logic-guided semantic representation learning model for zero-shot relation classification. |
JUAN LI et. al. | arxiv-cs.CL | 2020-10-30 |
| 128 | Towards Accurate And Consistent Evaluation: A Dataset For Distantly-Supervised Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this problem, we build a new dataset NYTH, where we use the DS-generated data as training data and hire annotators to label test data. |
TONG ZHU et. al. | arxiv-cs.CL | 2020-10-30 |
| 129 | RuREBus: A Case Study Of Joint Named Entity Recognition And Relation Extraction From E-Government Domain IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we describe the whole developed pipeline, starting from text annotation, baseline development, and designing a shared task in hopes of improving the baseline. |
VITALY IVANIN et. al. | arxiv-cs.CL | 2020-10-29 |
| 130 | WNUT-2020 Task 1 Overview: Extracting Entities And Relations From Wet Lab Protocols IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the results of the wet lab information extraction task at WNUT 2020. |
Jeniya Tabassum; Sydney Lee; Wei Xu; Alan Ritter; | arxiv-cs.CL | 2020-10-27 |
| 131 | RH-Net: Improving Neural Relation Extraction Via Reinforcement Learning and Hierarchical Relational Searching Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel framework named RH-Net, which utilizes Reinforcement learning and Hierarchical relational searching module to improve relation extraction. |
Jianing Wang; | arxiv-cs.CL | 2020-10-27 |
| 132 | Meta-Learning For Neural Relation Classification With Distant Supervision IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a meta-learning based approach, which learns to reweight noisy training data under the guidance of reference data. |
ZHENZHEN LI et. al. | arxiv-cs.CL | 2020-10-26 |
| 133 | TPLinker: Single-stage Joint Extraction Of Entities And Relations Through Token Pair Linking IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate the issue, we propose in this paper a one-stage joint extraction model, namely, TPLinker, which is capable of discovering overlapping relations sharing one or both entities while immune from the exposure bias. |
YUCHENG WANG et. al. | arxiv-cs.CL | 2020-10-26 |
| 134 | A Frustratingly Easy Approach for Entity and Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a simple pipelined approach for entity and relation extraction, and establish the new state-of-the-art on standard benchmarks (ACE04, ACE05 and SciERC), obtaining a 1.7%-2.8% absolute improvement in relation F1 over previous joint models with the same pre-trained encoders. |
Zexuan Zhong; Danqi Chen; | arxiv-cs.CL | 2020-10-24 |
| 135 | Effective Distant Supervision for Temporal Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a method of automatically collecting distantly-supervised examples of temporal relations. |
Xinyu Zhao; Shih-ting Lin; Greg Durrett; | arxiv-cs.CL | 2020-10-23 |
| 136 | Learning To Decouple Relations: Few-Shot Relation Classification With Entity-Guided Attention And Confusion-Aware Training IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To alleviate the above relation confusion problem, we propose CTEG, a model equipped with two mechanisms to learn to decouple these easily-confused relations. |
YINGYAO WANG et. al. | arxiv-cs.CL | 2020-10-21 |
| 137 | Document-Level Relation Extraction With Adaptive Thresholding And Localized Context Pooling IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose two novel techniques, adaptive thresholding and localized context pooling, to solve the multi-label and multi-entity problems. |
Wenxuan Zhou; Kevin Huang; Tengyu Ma; Jing Huang; | arxiv-cs.CL | 2020-10-21 |
| 138 | Exploit Multiple Reference Graphs For Semi-supervised Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle this limitation, we propose to build the connection between the unlabeled data and the labeled ones rather than directly mapping the unlabeled samples to the classes. |
Wanli Li; Tieyun Qian; | arxiv-cs.CL | 2020-10-21 |
| 139 | Bootleg: Chasing The Tail With Self-Supervised Named Entity Disambiguation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by these patterns, we introduce Bootleg, a self-supervised NED system that is explicitly grounded in reasoning patterns for disambiguation. |
LAUREL ORR et. al. | arxiv-cs.CL | 2020-10-20 |
| 140 | Neural Relation Extraction On Wikipedia Tables For Augmenting Knowledge Graphs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We help close this gap with a neural method that uses contextual information surrounding a table in a Wikipedia article to extract relations between entities appearing in the same row of a table or between the entity of said article and entities appearing in the table. |
Erin Macdonald; Denilson Barbosa; | cikm | 2020-10-19 |
| 141 | Mining Infrequent High-Quality Phrases From Domain-Specific Corpora IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on mining high-quality phrases from domain-specific corpora with special consideration of infrequent ones. |
LI WANG et. al. | cikm | 2020-10-19 |
| 142 | Enhance Prototypical Network With Text Descriptions For Few-shot Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose TD-Proto, which enhances prototypical network with relation and entity descriptions. |
KAIJIA YANG et. al. | cikm | 2020-10-19 |
| 143 | Cross-sentence N-ary Relation Extraction Using Entity Link And Discourse Relation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents an efficient method of extracting n-ary relations from multiple sentences which is called Entity-path and Discourse relation-centric Relation Extractor (EDCRE). |
SANGHAK LEE et. al. | cikm | 2020-10-19 |
| 144 | The RELX Dataset And Matching The Multilingual Blanks For Cross-Lingual Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this issue, we propose two cross-lingual relation classification models: a baseline model based on Multilingual BERT and a new multilingual pretraining setup, which significantly improves the baseline with distant supervision. For evaluation, we introduce a new public benchmark dataset for cross-lingual relation classification in English, French, German, Spanish, and Turkish, called RELX. We also provide the RELX-Distant dataset, which includes hundreds of thousands of sentences with relations from Wikipedia and Wikidata collected by distant supervision for these languages. |
Abdullatif Köksal; Arzucan Özgür; | arxiv-cs.CL | 2020-10-19 |
| 145 | Relation Extraction With Self-determined Graph Convolutional Network IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel model, the Self-determined Graph Convolutional Network (SGCN), which determines a weighted graph using a self-attention mechanism, rather using any linguistic tool. |
Sunil Kumar Sahu; Derek Thomas; Billy Chiu; Neha Sengupta; Mohammady Mahdy; | cikm | 2020-10-19 |
| 146 | T-REX: A Topic-Aware Relation Extraction Model IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle the problem, we propose a Topic-aware Relation EXtraction (T-REX) model. |
Woohwan Jung; Kyuseok Shim; | cikm | 2020-10-19 |
| 147 | Cross-Lingual Relation Extraction With Transformers IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a cross-lingual RE approach that does not require any human annotation in a target language or any cross-lingual resources. |
Jian Ni; Taesun Moon; Parul Awasthy; Radu Florian; | arxiv-cs.CL | 2020-10-16 |
| 148 | TDRE: A Tensor Decomposition Based Approach For Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: According to effective decomposition methods, we propose the Tensor Decomposition based Relation Extraction (TDRE) approach which is able to extract overlapping triplets and avoid detecting unnecessary entity pairs. |
Bin-Bin Zhao; Liang Li; Hui-Dong Zhang; | arxiv-cs.AI | 2020-10-15 |
| 149 | Named Entity Recognition And Relation Extraction Using Enhanced Table Filling By Contextualized Representations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, a novel method for extracting named entities and relations from unstructured text based on the table representation is presented. |
Youmi Ma; Tatsuya Hiraoka; Naoaki Okazaki; | arxiv-cs.CL | 2020-10-15 |
| 150 | Joint Constrained Learning for Event-Event Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Due to the lack of jointly labeled data for these relational phenomena and the restriction on the structures they articulate, we propose a joint constrained learning framework for modeling event-event relations. |
Haoyu Wang; Muhao Chen; Hongming Zhang; Dan Roth; | arxiv-cs.CL | 2020-10-13 |
| 151 | Visual Relation Of Interest Detection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel Visual Relation of Interest Detection (VROID) task, which aims to detect visual relations that are important for conveying the main content of an image, motivated from the intuition that not all correctly detected relations are really "interesting" in semantics and only a fraction of them really make sense for representing the image main content. |
Fan Yu; Haonan Wang; Tongwei Ren; Jinhui Tang; Gangshan Wu; | mm | 2020-10-12 |
| 152 | HOSE-Net: Higher Order Structure Embedded Network For Scene Graph Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Accordingly, in this paper, we propose a Higher Order Structure Embedded Network (HOSE-Net) to mitigate this issue. |
Meng Wei; Chun Yuan; Xiaoyu Yue; Kuo Zhong; | mm | 2020-10-12 |
| 153 | Video Relation Detection Via Multiple Hypothesis Association IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel relation association method called Multiple Hypothesis Association (MHA). |
ZIXUAN SU et. al. | mm | 2020-10-12 |
| 154 | Relation Classification As Two-way Span-Prediction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a span-prediction based system for RC and evaluate its performance compared to the embedding based system. |
Amir DN Cohen; Shachar Rosenman; Yoav Goldberg; | arxiv-cs.CL | 2020-10-09 |
| 155 | Improving Long-Tail Relation Extraction With Collaborating Relation-Augmented Attention IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel neural network, Collaborating Relation-augmented Attention (CoRA), to handle both the wrong labeling and long-tail relations. |
YANG LI et. al. | arxiv-cs.CL | 2020-10-08 |
| 156 | Understanding Clinical Trial Reports: Extracting Medical Entities And Their Relations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce new data for this task, and evaluate models that have recently achieved state-of-the-art results on similar tasks in Natural Language Processing. |
BENJAMIN E. NYE et. al. | arxiv-cs.CL | 2020-10-07 |
| 157 | Learning From Context Or Names? An Empirical Study On Neural Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Based on the analyses, we propose an entity-masked contrastive pre-training framework for RE to gain a deeper understanding on both textual context and type information while avoiding rote memorization of entities or use of superficial cues in mentions. |
HAO PENG et. al. | arxiv-cs.CL | 2020-10-05 |
| 158 | RDSGAN: Rank-based Distant Supervision Relation Extraction With Generative Adversarial Framework IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel generative neural framework named RDSGAN (Rank-based Distant Supervision GAN) which automatically generates valid instances for distant supervision relation extraction. |
Guoqing Luo; Jiaxin Pan; Min Peng; | arxiv-cs.CL | 2020-09-30 |
| 159 | Reinforcement Learning-based N-ary Cross-Sentence Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we relax this strong assumption by a weaker distant supervision assumption to address the second issue and propose a novel sentence distribution estimator model to address the first problem. |
Chenhan Yuan; Ryan Rossi; Andrew Katz; Hoda Eldardiry; | arxiv-cs.LG | 2020-09-26 |
| 160 | Clustering-based Unsupervised Generative Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a Clustering-based Unsupervised generative Relation Extraction (CURE) framework that leverages an Encoder-Decoder architecture to perform self-supervised learning so the encoder can extract relation information. |
Chenhan Yuan; Ryan Rossi; Andrew Katz; Hoda Eldardiry; | arxiv-cs.CL | 2020-09-26 |
| 161 | DWIE: An Entity-centric Dataset for Multi-task Document-level Information Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents DWIE, the ‘Deutsche Welle corpus for Information Extraction’, a newly created multi-task dataset that combines four main Information Extraction (IE) annotation subtasks: (i) Named Entity Recognition (NER), (ii) Coreference Resolution, (iii) Relation Extraction (RE), and (iv) Entity Linking. |
Klim Zaporojets; Johannes Deleu; Chris Develder; Thomas Demeester; | arxiv-cs.CL | 2020-09-26 |
| 162 | A Comparative Study On Structural And Semantic Properties Of Sentence Embeddings IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the aforementioned properties by evaluating the extent to which sentences carrying similar senses are embedded in close proximity sub-spaces, and if we can exploit that structure to align sentences to a knowledge graph. We propose a set of experiments using a widely-used large-scale data set for relation extraction and focusing on a set of key sentence embedding methods. |
Alexander Kalinowski; Yuan An; | arxiv-cs.CL | 2020-09-23 |
| 163 | Let’s Stop Incorrect Comparisons In End-to-end Relation Extraction! IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This meta-analysis emphasizes the need for rigor in the report of both the evaluation setting and the datasets statistics and we call for unifying the evaluation setting in end-to-end RE. |
Bruno Taillé; Vincent Guigue; Geoffrey Scoutheeten; Patrick Gallinari; | arxiv-cs.CL | 2020-09-22 |
| 164 | AutoRC: Improving BERT Based Relation Classification Models Via Architecture Search IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we design a comprehensive search space for BERT based RC models and employ neural architecture search (NAS) method to automatically discover the design choices mentioned above. |
Wei Zhu; Xipeng Qiu; Yuan Ni; Guotong Xie; | arxiv-cs.CL | 2020-09-22 |
| 165 | Relation Extraction From Biomedical And Clinical Text: Unified Multitask Learning Framework IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the relation extraction task from three major biomedical and clinical tasks, namely drug-drug interaction, protein-protein interaction, and medical concept relation extraction. |
Shweta Yadav; Srivatsa Ramesh; Sriparna Saha; Asif Ekbal; | arxiv-cs.CL | 2020-09-20 |
| 166 | RECON: Relation Extraction Using Knowledge Graph Context in A Graph Neural Network IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a novel method named RECON, that automatically identifies relations in a sentence (sentential relation extraction) and aligns to a knowledge graph (KG). |
ANSON BASTOS et. al. | arxiv-cs.CL | 2020-09-18 |
| 167 | Deep Learning Approaches For Extracting Adverse Events And Indications Of Dietary Supplements From Clinical Text IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The objective of our work is to demonstrate the feasibility of utilizing deep learning models to extract safety signals related to the use of dietary supplements (DS) in clinical text. |
Yadan Fan; Sicheng Zhou; Yifan Li; Rui Zhang; | arxiv-cs.IR | 2020-09-16 |
| 168 | Leveraging Semantic Parsing For Relation Linking Over Knowledge Bases IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these challenges, we present SLING, a relation linking framework which leverages semantic parsing using Abstract Meaning Representation (AMR) and distant supervision. |
NANDANA MIHINDUKULASOORIYA et. al. | arxiv-cs.CL | 2020-09-16 |
| 169 | The Devil Is The Classifier: Investigating Long Tail Relation Classification With Decoupling Analysis IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we conduct an in-depth empirical investigation into the long-tailed problem and found that pre-trained models with instance-balanced sampling already capture the well-learned representations for all classes; moreover, it is possible to achieve better long-tailed classification ability at low cost by only adjusting the classifier. |
HAIYANG YU et. al. | arxiv-cs.LG | 2020-09-15 |
| 170 | Cascaded Models For Better Fine-Grained Named Entity Recognition IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present a cascaded approach to labeling fine-grained NER, applying to a newly released fine-grained NER dataset that was used in the TAC KBP 2019 evaluation (Ji et al., 2019), inspired by the fact that training data is available for some of the coarse labels. |
Parul Awasthy; Taesun Moon; Jian Ni; Radu Florian; | arxiv-cs.CL | 2020-09-15 |
| 171 | On Robustness and Bias Analysis of BERT-based Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we analyze a fine-tuned BERT model from different perspectives using relation extraction. |
LUOQIU LI et. al. | arxiv-cs.CL | 2020-09-14 |
| 172 | Semantic Relations and Deep Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: A new Chapter 5 of the book, by Vivi Nastase and Stan Szpakowicz, discusses relation classification/extraction in the deep-learning paradigm which arose after the first edition appeared. |
Vivi Nastase; Stan Szpakowicz; | arxiv-cs.CL | 2020-09-11 |
| 173 | UPB At SemEval-2020 Task 6: Pretrained Language Models For Definition Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work presents our contribution in the context of the 6th task of SemEval-2020: Extracting Definitions from Free Text in Textbooks (DeftEval). |
Andrei-Marius Avram; Dumitru-Clementin Cercel; Costin-Gabriel Chiru; | arxiv-cs.CL | 2020-09-11 |
| 174 | Relation Detection For Indonesian Language Using Deep Neural Network — Support Vector Machine Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we employ neural network to do relation detection between two named entities for Indonesian Language. |
Ramos Janoah Hasudungan; Ayu Purwarianti; | arxiv-cs.CL | 2020-09-11 |
| 175 | Dialogue Relation Extraction With Document-level Heterogeneous Graph Attention Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We empirically show that this graph-based approach quite effectively captures the relations between different entity pairs in a dialogue as it outperforms the state-of-the-art approaches by a significant margin on the benchmark dataset DialogRE. |
Hui Chen; Pengfei Hong; Wei Han; Navonil Majumder; Soujanya Poria; | arxiv-cs.CL | 2020-09-10 |
| 176 | Meta-Learning With Sparse Experience Replay For Lifelong Language Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel approach to lifelong learning of language tasks based on meta-learning with sparse experience replay that directly optimizes to prevent forgetting. |
Nithin Holla; Pushkar Mishra; Helen Yannakoudakis; Ekaterina Shutova; | arxiv-cs.CL | 2020-09-10 |
| 177 | Revisiting LSTM Networks For Semi-Supervised Text Classification Via Mixed Objective Function IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study bidirectional LSTM network for the task of text classification using both supervised and semi-supervised approaches. |
Devendra Singh Sachan; Manzil Zaheer; Ruslan Salakhutdinov; | arxiv-cs.CL | 2020-09-08 |
| 178 | High-throughput Relation Extraction Algorithm Development Associating Knowledge Articles And Electronic Health Records IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present Hi-RES, a framework for high-throughput relation extraction algorithm development. |
Yucong Lin; Keming Lu; Yulin Chen; Chuan Hong; Sheng Yu; | arxiv-cs.LG | 2020-09-07 |
| 179 | Extracting Semantic Concepts And Relations From Scientific Publications By Using Deep Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The aim of this paper is to introduce a proposal of automatically extracting semantic concepts and relations from scientific publications. |
Fatima N. AL-Aswadi; Huah Yong Chan; Keng Hoon Gan; | arxiv-cs.CL | 2020-09-01 |
| 180 | SemEval-2020 Task 6: Definition Extraction From Free Text With The DEFT Corpus IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present DeftEval, a SemEval shared task in which participants must extract definitions from free text using a term-definition pair corpus that reflects the complex reality of definitions in natural language. |
Sasha Spala; Nicholas A Miller; Franck Dernoncourt; Carl Dockhorn; | arxiv-cs.CL | 2020-08-31 |
| 181 | Two Step Joint Model For Drug Drug Interaction Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead of regarding task1 as named entity recognition (NER) task and regarding task2 as relation extraction (RE) task then solving it in a pipeline, we propose a two step joint model to detect DDI and it’s related mentions jointly. |
SILIANG TANG et. al. | arxiv-cs.CL | 2020-08-28 |
| 182 | Entity And Evidence Guided Relation Extraction For DocRED IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we pro-pose a joint training frameworkE2GRE(Entity and Evidence Guided Relation Extraction)for this task. |
Kevin Huang; Guangtao Wang; Tengyu Ma; Jing Huang; | arxiv-cs.CL | 2020-08-27 |
| 183 | Behind The Scene: Revealing The Secrets Of Pre-trained Vision-and-Language Models IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To reveal the secrets behind the scene, we present VALUE (Vision-And-Language Understanding Evaluation), a set of meticulously designed probing tasks (e.g., Visual Coreference Resolution, Visual Relation Detection) generalizable to standard pre-trained V+L models, to decipher the inner workings of multimodal pre-training (e.g., implicit knowledge garnered in individual attention heads, inherent cross-modal alignment learned through contextualized multimodal embeddings). |
JIZE CAO et. al. | eccv | 2020-08-21 |
| 184 | Do Syntax Trees Help Pre-trained Transformers Extract Information? IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we systematically study the utility of incorporating dependency trees into pre-trained transformers on three representative information extraction tasks: semantic role labeling (SRL), named entity recognition, and relation extraction. |
Devendra Singh Sachan; Yuhao Zhang; Peng Qi; William Hamilton; | arxiv-cs.CL | 2020-08-20 |
| 185 | An Annotated Corpus Of Webtables For Information Extraction Tasks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce an annotation framework and a dataset of 217,834 tables from Wikipedia which are annotated with 28 relations, using both classifiers and carefully designed queries over a reference knowledge graph. |
Erin Macdonald; Denilson Barbosa; | arxiv-cs.IR | 2020-08-17 |
| 186 | Distantly Supervised Relation Extraction In Federated Settings IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a federated denoising framework to suppress label noise in federated settings. |
Dianbo Sui; Yubo Chen; Kang Liu; Jun Zhao; | arxiv-cs.CL | 2020-08-11 |
| 187 | Improving Performance Of Relation Extraction Algorithm Via Leveled Adversarial PCNN And Database Expansion IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This study introduces database expansion using the Minimum Description Length (MDL) algorithm to expand the database for better relation extraction. |
Diyah Puspitaningrum; | arxiv-cs.IR | 2020-07-29 |
| 188 | NoPropaganda At SemEval-2020 Task 11: A Borrowed Approach To Sequence Tagging And Text Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes our contribution to SemEval-2020 Task 11: Detection Of Propaganda Techniques In News Articles. |
Ilya Dimov; Vladislav Korzun; Ivan Smurov; | arxiv-cs.CL | 2020-07-25 |
| 189 | Learning Latent Forests For Medical Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel model which treats the dependency structure as a latent variable and induces it from the unstructured text in an end-to-end fashion. |
Zhijiang Guo; Guoshun Nan; Wei LU; Shay B. Cohen; | ijcai | 2020-07-21 |
| 190 | On The Importance Of Word And Sentence Representation Learning In Implicit Discourse Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We argue that a powerful contextualized representation module, a bilateral multi-perspective matching module, and a global information fusion module are all important to implicit discourse analysis. We propose a novel model to combine these modules together. |
Xin Liu; Jiefu Ou; Yangqiu Song; Xin Jiang; | ijcai | 2020-07-21 |
| 191 | A Relation-Specific Attention Network For Joint Entity And Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a relation-specific attention network (RSAN) to handle the issue. |
YUE YUAN et. al. | ijcai | 2020-07-21 |
| 192 | Attention As Relation: Learning Supervised Multi-head Self-Attention For Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an attention-based joint model, which mainly contains an entity extraction module and a relation detection module, to address the challenges. |
JIE LIU et. al. | ijcai | 2020-07-21 |
| 193 | Modeling Dense Cross-Modal Interactions For Joint Entity-Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a deep Cross-Modal Attention Network (CMAN) for joint entity and relation extraction. |
Shan Zhao; Minghao Hu; Zhiping Cai; Fang Liu; | ijcai | 2020-07-21 |
| 194 | Asking Effective And Diverse Questions: A Machine Reading Comprehension Based Framework For Joint Entity-Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we improve the existing MRC-based entity-relation extraction model through diverse question answering. |
Tianyang Zhao; Zhao Yan; Yunbo Cao; Zhoujun Li; | ijcai | 2020-07-21 |
| 195 | Few-shot Relation Extraction Via Bayesian Meta-learning On Task Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel Bayesian meta-learning approach to effectively learn the posterior distributions of the prototype vectors of tasks, where the initial prior of the prototype vectors is parameterized with a graph neural network on the global task graph. |
Meng Qu; Tianyu Gao; Louis-Pascal Xhonneux; Jian Tang; | icml | 2020-07-11 |
| 196 | Few-shot Relation Extraction Via Bayesian Meta-learning On Relation Graphs IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel Bayesian meta-learning approach to effectively learn the posterior distribution of the prototype vectors of relations, where the initial prior of the prototype vectors is parameterized with a graph neural network on the global relation graph. |
Meng Qu; Tianyu Gao; Louis-Pascal A. C. Xhonneux; Jian Tang; | arxiv-cs.LG | 2020-07-05 |
| 197 | Pynsett: A Programmable Relation Extractor IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a programmable relation extraction method for the English language by parsing texts into semantic graphs. |
Alberto Cetoli; | arxiv-cs.CL | 2020-07-04 |
| 198 | TURL: Table Understanding Through Representation Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present TURL, a novel framework that introduces the pre-training/fine-tuning paradigm to relational Web tables. |
Xiang Deng; Huan Sun; Alyssa Lees; You Wu; Cong Yu; | arxiv-cs.IR | 2020-06-26 |
| 199 | NLPContributions: An Annotation Scheme For Machine Reading Of Scholarly Contributions In Natural Language Processing Literature IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this article, we describe the outcomes of this pilot annotation phase. |
Jennifer D’Souza; Sören Auer; | arxiv-cs.CL | 2020-06-23 |
| 200 | Reasoning With Latent Structure Refinement For Document-Level Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Unlike previous methods that may not be able to capture rich non-local interactions for inference, we propose a novel model that empowers the relational reasoning across sentences by automatically inducing the latent document-level graph. |
Guoshun Nan; Zhijiang Guo; Ivan Sekulic; Wei Lu; | acl | 2020-06-20 |
| 201 | ZeroShotCeres: Zero-Shot Relation Extraction From Semi-Structured Webpages IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a solution for zero-shot open-domain relation extraction from webpages with a previously unseen template, including from websites with little overlap with existing sources of knowledge for distant supervision and websites in entirely new subject verticals. |
Colin Lockard; Prashant Shiralkar; Xin Luna Dong; Hannaneh Hajishirzi; | acl | 2020-06-20 |
| 202 | In Layman’s Terms: Semi-Open Relation Extraction From Scientific Texts IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we combine the output of both types of systems to achieve Semi-Open Relation Extraction, a new task that we explore in the Biology domain. |
Ruben Kruiper; Julian Vincent; Jessica Chen-Burger; Marc Desmulliez; Ioannis Konstas; | acl | 2020-06-20 |
| 203 | Synchronous Double-channel Recurrent Network For Aspect-Opinion Pair Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore Aspect-Opinion Pair Extraction (AOPE) task, which aims at extracting aspects and opinion expressions in pairs. To verify the performance of SDRN, we manually build three datasets based on SemEval 2014 and 2015 benchmarks. |
Shaowei Chen; Jie Liu; Yu Wang; Wenzheng Zhang; Ziming Chi; | acl | 2020-06-20 |
| 204 | Generalizing Natural Language Analysis Through Span-relation Representations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we provide the simple insight that a great variety of tasks can be represented in a single unified format consisting of labeling spans and relations between spans, thus a single task-independent model can be used across different tasks. |
Zhengbao Jiang; Wei Xu; Jun Araki; Graham Neubig; | acl | 2020-06-20 |
| 205 | ExpBERT: Representation Engineering With Natural Language Explanations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we allow model developers to specify these types of inductive biases as natural language explanations. |
Shikhar Murty; Pang Wei Koh; Percy Liang; | acl | 2020-06-20 |
| 206 | Relabel The Noise: Joint Extraction Of Entities And Relations Via Cooperative Multiagents IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a joint extraction approach to address this problem by re-labeling noisy instances with a group of cooperative multiagents. |
Daoyuan Chen; Yaliang Li; Kai Lei; Ying Shen; | acl | 2020-06-20 |
| 207 | Dialogue-Based Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present the first human-annotated dialogue-based relation extraction (RE) dataset DialogRE, aiming to support the prediction of relation(s) between two arguments that appear in a dialogue. |
Dian Yu; Kai Sun; Claire Cardie; Dong Yu; | acl | 2020-06-20 |
| 208 | Implicit Discourse Relation Classification: We Need To Talk About Evaluation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we highlight these inconsistencies and propose an improved evaluation protocol. |
Najoung Kim; Song Feng; Chulaka Gunasekara; Luis Lastras; | acl | 2020-06-20 |
| 209 | Probing Linguistic Features Of Sentence-Level Representations In Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce 14 probing tasks targeting linguistic properties relevant to RE, and we use them to study representations learned by more than 40 different encoder architecture and linguistic feature combinations trained on two datasets, TACRED and SemEval 2010 Task 8. |
Christoph Alt; Aleksandra Gabryszak; Leonhard Hennig; | acl | 2020-06-20 |
| 210 | Revisiting Unsupervised Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: However, we demonstrate that by using only named entities to induce relation types, we can outperform existing methods on two popular datasets. |
Thy Thy Tran; Phong Le; Sophia Ananiadou; | acl | 2020-06-20 |
| 211 | SpanMlt: A Span-based Multi-Task Learning Framework For Pair-wise Aspect And Opinion Terms Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, this paper proposes an end-to-end method to solve the task of Pair-wise Aspect and Opinion Terms Extraction (PAOTE). |
He Zhao; Longtao Huang; Rong Zhang; Quan Lu; hui xue; | acl | 2020-06-20 |
| 212 | Relation Extraction With Explanation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we annotate a test set with ground-truth sentence-level explanations to evaluate the quality of explanations afforded by the relation extraction models. |
Hamed Shahbazi; Xiaoli Fern; Reza Ghaeini; Prasad Tadepalli; | acl | 2020-06-20 |
| 213 | TACRED Revisited: A Thorough Evaluation Of The TACRED Relation Extraction Task IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate the questions: Have we reached a performance ceiling or is there still room for improvement? |
Christoph Alt; Aleksandra Gabryszak; Leonhard Hennig; | acl | 2020-06-20 |
| 214 | Exploiting The Syntax-Model Consistency For Neural Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to overcome these issues, we propose a novel deep learning model for RE that uses the dependency trees to extract the syntax-based importance scores for the words, serving as a tree representation to introduce syntactic information into the models with greater generalization. |
Amir Pouran Ben Veyseh; Franck Dernoncourt; Dejing Dou; Thien Huu Nguyen; | acl | 2020-06-20 |
| 215 | Extracting N-ary Cross-sentence Relations Using Constrained Subsequence Kernel IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a new formulation of the relation extraction task where the relations are more general than intra-sentence relations in the sense that they may span multiple sentences and may have more than two arguments. |
Sachin Pawar; Pushpak Bhattacharyya; Girish K. Palshikar; | arxiv-cs.CL | 2020-06-15 |
| 216 | Human Brain Activity For Machine Attention IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We devise a method for finding such EEG features to supervise machine attention through combining theoretically motivated cropping with random forest tree splits. |
Lukas Muttenthaler; Nora Hollenstein; Maria Barrett; | arxiv-cs.CL | 2020-06-09 |
| 217 | Cascaded Human-Object Interaction Recognition IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Considering the intrinsic complexity of the task, we introduce a cascade architecture for a multi-stage, coarse-to-fine HOI understanding. |
Tianfei Zhou; Wenguan Wang; Siyuan Qi; Haibin Ling; Jianbing Shen; | cvpr | 2020-06-08 |
| 218 | Beyond Short-Term Snippet: Video Relation Detection With Spatio-Temporal Global Context IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these issues, this work proposes a novel sliding-window scheme to simultaneously predict short-term and long-term relationships. |
Chenchen Liu; Yang Jin; Kehan Xu; Guoqiang Gong; Yadong Mu; | cvpr | 2020-06-08 |
| 219 | Semantic Loss Application To Entity Relation Recognition IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: The main contribution of this paper is an end-to-end neural model for joint entity relation extraction which incorporates a novel loss function. |
Venkata Sasank Pagolu; | arxiv-cs.CL | 2020-06-06 |
| 220 | Relation Of The Relations: A New Paradigm Of The Relation Extraction Problem IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Due to the significance of RoR in existing datasets, we propose a new paradigm of RE that considers as a whole the predictions of all relations in the same context. |
Zhijing Jin; Yongyi Yang; Xipeng Qiu; Zheng Zhang; | arxiv-cs.CL | 2020-06-05 |
| 221 | Benchmarking BioRelEx For Entity Tagging And Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to fill this gap, we compare multiple existing entity and relation extraction models over a recently introduced public dataset, BioRelEx of sentences annotated with biological entities and relations. |
Abhinav Bhatt; Kaustubh D. Dhole; | arxiv-cs.CL | 2020-05-31 |
| 222 | Recognizing Chinese Judicial Named Entity Using BiLSTM-CRF IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, in this paper, we propose a deep learning-based method named BiLSTM-CRF which consists of bi-directional long short-term memory (BiLSTM) and conditional random fields (CRF). |
PIN TANG et. al. | arxiv-cs.CL | 2020-05-31 |
| 223 | A Comparative Study Of Lexical Substitution Approaches Based On Neural Language Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a large-scale comparative study of popular neural language and masked language models (LMs and MLMs), such as context2vec, ELMo, BERT, XLNet, applied to the task of lexical substitution. |
Nikolay Arefyev; Boris Sheludko; Alexander Podolskiy; Alexander Panchenko; | arxiv-cs.CL | 2020-05-29 |
| 224 | Relation Extraction With Explanation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we annotate a test set with ground-truth sentence-level explanations to evaluate the quality of explanations afforded by the relation extraction models. |
Hamed Shahbazi; Xiaoli Z. Fern; Reza Ghaeini; Prasad Tadepalli; | arxiv-cs.IR | 2020-05-28 |
| 225 | A Data-driven Approach For Noise Reduction In Distantly Supervised Biomedical Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We aim to reduce such noise by extending an entity-enriched relation classification BERT model to the problem of multiple instance learning, and defining a simple data encoding scheme that significantly reduces noise, reaching state-of-the-art performance for distantly-supervised biomedical relation extraction. |
Saadullah Amin; Katherine Ann Dunfield; Anna Vechkaeva; Günter Neumann; | arxiv-cs.CL | 2020-05-26 |
| 226 | Semi-Automating Knowledge Base Construction For Cancer Genetics IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we consider the exponentially growing subarea of genetics in cancer. |
Somin Wadhwa; Kanhua Yin; Kevin S. Hughes; Byron C. Wallace; | arxiv-cs.CL | 2020-05-16 |
| 227 | A Scientific Information Extraction Dataset For Nature Inspired Engineering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper describes a dataset of 1,500 manually-annotated sentences that express domain-independent relations between central concepts in a scientific biology text, such as trade-offs and correlations. |
Ruben Kruiper; Julian F. V. Vincent; Jessica Chen-Burger; Marc P. Y. Desmulliez; Ioannis Konstas; | arxiv-cs.CL | 2020-05-15 |
| 228 | In Layman’s Terms: Semi-Open Relation Extraction From Scientific Texts IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work we combine the output of both types of systems to achieve Semi-Open Relation Extraction, a new task that we explore in the Biology domain. |
Ruben Kruiper; Julian F. V. Vincent; Jessica Chen-Burger; Marc P. Y. Desmulliez; Ioannis Konstas; | arxiv-cs.CL | 2020-05-15 |
| 229 | An Evaluation Of Recent Neural Sequence Tagging Models In Turkish Named Entity Recognition IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we empirically investigate the use of recent neural architectures (Bidirectional long short-term memory and Transformer-based networks) proposed for Turkish NER tagging in the same setting. |
Gizem Aras; Didem Makaroglu; Seniz Demir; Altan Cakir; | arxiv-cs.CL | 2020-05-14 |
| 230 | Reasoning With Latent Structure Refinement For Document-Level Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Unlike previous methods that may not be able to capture rich non-local interactions for inference, we propose a novel model that empowers the relational reasoning across sentences by automatically inducing the latent document-level graph. |
Guoshun Nan; Zhijiang Guo; Ivan Sekulić; Wei Lu; | arxiv-cs.CL | 2020-05-13 |
| 231 | NERO: A Neural Rule Grounding Framework For Label-Efficient Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a neural approach to ground rules for RE, named Nero, which jointly learns a relation extraction module and a soft matching module. |
WENXUAN ZHOU et. al. | www | 2020-05-13 |
| 232 | Relation Adversarial Network For Low Resource Knowledge Graph Completion IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim at predicting new facts under a challenging setting where only limited training instances are available. |
NINGYU ZHANG et. al. | www | 2020-05-13 |
| 233 | LOREM: Language-consistent Open Relation Extraction From Unstructured Text IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a Language-consistent multi-lingual Open Relation Extraction Model (LOREM) for finding relation tuples of any type between entities in unstructured texts. |
Tom Harting; Sepideh Mesbah; Christoph Lofi; | www | 2020-05-13 |
| 234 | PERLEX: A Bilingual Persian-English Gold Dataset For Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present PERLEX as the first Persian dataset for relation extraction, which is an expert-translated version of the Semeval-2010-Task-8 dataset. |
Majid Asgari-Bidhendi; Mehrdad Nasser; Behrooz Janfada; Behrouz Minaei-Bidgoli; | arxiv-cs.CL | 2020-05-13 |
| 235 | Adversarial Learning For Supervised And Semi-supervised Relation Extraction In Biomedical Literature IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate adversarial training with multiple adversarial examples to benefit the relation extraction task. |
Peng Su; K. Vijay-Shanker; | arxiv-cs.CL | 2020-05-08 |
| 236 | An Empirical Study Of Multi-Task Learning On BERT For Biomedical Text Mining IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study a multi-task learning model with multiple decoders on varieties of biomedical and clinical natural language processing tasks such as text similarity, relation extraction, named entity recognition, and text inference. |
Yifan Peng; Qingyu Chen; Zhiyong Lu; | arxiv-cs.CL | 2020-05-06 |
| 237 | FarsBase-KBP: A Knowledge Base Population System For The Persian Knowledge Graph IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a knowledge base population system for the Persian language, which extracts knowledge from unlabeled raw text, crawled from the Web. To evaluate the performance of the presented knowledge base population system, we present the first gold dataset for benchmarking knowledge base population in the Persian language, which consisting of 22015 FarsBase triples and verified by human experts. |
Majid Asgari-Bidhendi; Behrooz Janfada; Behrouz Minaei-Bidgoli; | arxiv-cs.CL | 2020-05-04 |
| 238 | PyBART: Evidence-based Syntactic Transformations For IE IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a broad-coverage, data-driven and linguistically sound set of transformations, that makes event-structure and many lexical relations explicit. |
Aryeh Tiktinsky; Yoav Goldberg; Reut Tsarfaty; | arxiv-cs.CL | 2020-05-04 |
| 239 | Distantly-Supervised Neural Relation Extraction With Side Information Using BERT IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Considering that this method outperformed state-of-the-art baselines, in this paper, we propose a related approach to RESIDE also using additional side information, but simplifying the sentence encoding with BERT embeddings. |
Johny Moreira; Chaina Oliveira; David Macêdo; Cleber Zanchettin; Luciano Barbosa; | arxiv-cs.CL | 2020-04-29 |
| 240 | Exploring The Suitability Of Semantic Spaces As Word Association Models For The Extraction Of Semantic Relationships IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we empirically study and explore the potential of a novel idea of using classical semantic spaces and models, e.g., Word Embedding, generated for extracting word association, in conjunction with relation extraction approaches. |
Epaminondas Kapetanios; Vijayan Sugumaran; Anastassia Angelopoulou; | arxiv-cs.CL | 2020-04-29 |
| 241 | A Practical Framework For Relation Extraction With Noisy Labels Based On Doubly Transitional Loss IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we introduce a practical end-to-end deep learning framework, including a standard feature extractor and a novel noisy classifier with our proposed doubly transitional mechanism. |
Shanchan Wu; Kai Fan; | arxiv-cs.CL | 2020-04-28 |
| 242 | MICK: A Meta-Learning Framework For Few-shot Relation Classification With Small Training Data IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we tackle an even harder problem by further limiting the amount of data available at training time. Additionally, we construct a brand new dataset: the TinyRel-CM dataset, a few-shot relation classification dataset in health domain with purposely small training data and challenging relation classes. |
Xiaoqing Geng; Xiwen Chen; Kenny Q. Zhu; Libin Shen; Yinggong Zhao; | arxiv-cs.CL | 2020-04-26 |
| 243 | Contextualised Graph Attention For Improved Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a contextualized graph attention network that combines edge features and multiple sub-graphs for improving relation extraction. |
Angrosh Mandya; Danushka Bollegala; Frans Coenen; | arxiv-cs.CL | 2020-04-22 |
| 244 | Learning Relation Ties With A Force-Directed Graph In Distant Supervised Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve this problem, in this paper, we propose a novel force-directed graph based relation extraction model to comprehensively learn relation ties. |
Yuming Shang; Heyan Huang; Xin Sun; Xianling Mao; | arxiv-cs.CL | 2020-04-21 |
| 245 | Improving Neural Relation Extraction With Implicit Mutual Relations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In contrast to existing distant supervision approaches that suffer from insufficient training corpora to extract relations, our proposal of mining implicit mutual relation from the massive unlabeled corpora transfers the semantic information of entity pairs into the RE model, which is more expressive and semantically plausible. |
J. Kuang; Y. Cao; J. Zheng; X. He; M. Gao and A. Zhou; | icde | 2020-04-20 |
| 246 | Probing Linguistic Features Of Sentence-Level Representations In Neural Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce 14 probing tasks targeting linguistic properties relevant to RE, and we use them to study representations learned by more than 40 different encoder architecture and linguistic feature combinations trained on two datasets, TACRED and SemEval 2010 Task 8. |
Christoph Alt; Aleksandra Gabryszak; Leonhard Hennig; | arxiv-cs.CL | 2020-04-17 |
| 247 | LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning From Explanation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: On three popular NLP tasks (named entity recognition, relation extraction, sentiment analysis), we find that using this enhanced supervision allows our models to surpass competitive baseline F1 scores by more than 5-10 percentage points, while using 2X times fewer labeled instances. |
DONG-HO LEE et. al. | arxiv-cs.CL | 2020-04-16 |
| 248 | Improving Scholarly Knowledge Representation: Evaluating BERT-based Models For Scientific Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this end, we present a thorough empirical evaluation on eight Bert-based classification models by focusing on two key factors: 1) Bert model variants, and 2) classification strategies. |
Ming Jiang; Jennifer D’Souza; Sören Auer; J. Stephen Downie; | arxiv-cs.DL | 2020-04-13 |
| 249 | Robustly Pre-trained Neural Model For Direct Temporal Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Methods: We studied several variants of BERT (Bidirectional Encoder Representations using Transformers) some involving clinical domain customization and the others involving improved architecture and/or training strategies. |
Hong Guan; Jianfu Li; Hua Xu; Murthy Devarakonda; | arxiv-cs.CL | 2020-04-13 |
| 250 | A Corpus Study And Annotation Schema For Named Entity Recognition And Relation Extraction Of Business Products IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a corpus study, an annotation schema and associated guidelines, for the annotation of product entity and company-product relation mentions. We also describe our ongoing annotation effort, and present a preliminary corpus of English web and social media documents annotated according to the proposed guidelines. |
Saskia Schön; Veselina Mironova; Aleksandra Gabryszak; Leonhard Hennig; | arxiv-cs.CL | 2020-04-07 |
| 251 | A German Corpus For Fine-Grained Named Entity Recognition And Relation Extraction Of Traffic And Industry Events IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work describes a corpus of German-language documents which has been annotated with fine-grained geo-entities, such as streets, stops and routes, as well as standard named entity types. |
MARTIN SCHIERSCH et. al. | arxiv-cs.CL | 2020-04-07 |
| 252 | Efficient Long-distance Relation Extraction With DG-SpanBERT IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Here, we propose a novel SpanBERT-based graph convolutional network (DG-SpanBERT) that extracts semantic features from a raw sentence using the pre-trained language model SpanBERT and a graph convolutional network to pool latent features. |
Jun Chen; Robert Hoehndorf; Mohamed Elhoseiny; Xiangliang Zhang; | arxiv-cs.CL | 2020-04-07 |
| 253 | Downstream Model Design Of Pre-trained Language Model For Relation Extraction Task IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, a new network architecture with a special loss function is designed to serve as a downstream model of PLMs for supervised relation extraction. |
Cheng Li; Ye Tian; | arxiv-cs.CL | 2020-04-07 |
| 254 | More Data, More Relations, More Context And More Openness: A Review And Outlook For Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we look back at existing RE methods, analyze key challenges we are facing nowadays, and show promising directions towards more powerful RE. |
XU HAN et. al. | arxiv-cs.CL | 2020-04-07 |
| 255 | SelfORE: Self-supervised Relational Feature Learning For Open Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we proposed a self-supervised framework named SelfORE, which exploits weak, self-supervised signals by leveraging large pretrained language model for adaptive clustering on contextualized relational features, and bootstraps the self-supervised signals by improving contextualized features in relation classification. |
Xuming Hu; Chenwei Zhang; Yusong Xu; Lijie Wen; Philip S. Yu; | arxiv-cs.CL | 2020-04-06 |
| 256 | Named Entities In Medical Case Reports: Corpus And Experiments IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the case reports, we annotate cases, conditions, findings, factors and negation modifiers. We present a new corpus comprising annotations of medical entities in case reports, originating from PubMed Central’s open access library. |
Sarah Schulz; Jurica Ševa; Samuel Rodriguez; Malte Ostendorff; Georg Rehm; | arxiv-cs.CL | 2020-03-29 |
| 257 | HIN: Hierarchical Inference Network For Document-Level Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Hierarchical Inference Network (HIN) to make full use of the abundant information from entity level, sentence level and document level. |
HENGZHU TANG et. al. | arxiv-cs.CL | 2020-03-28 |
| 258 | Common-Knowledge Concept Recognition For SEVA IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We use a pre-trained language model and fine-tune it with the labeled dataset of concepts. With the help of a domain expert and text processing methods, we construct a dataset annotated at the word-level by carefully defining a labelling scheme to train a sequence model to recognize systems engineering concepts. In addition, we also create some essential datasets for information such as abbreviations and definitions from the systems engineering domain. |
Jitin Krishnan; Patrick Coronado; Hemant Purohit; Huzefa Rangwala; | arxiv-cs.CL | 2020-03-25 |
| 259 | Cross-Lingual Adaptation Using Universal Dependencies IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We describe a cross-lingual adaptation method based on syntactic parse trees obtained from the Universal Dependencies (UD), which are consistent across languages, to develop classifiers in low-resource languages. |
Nasrin Taghizadeh; Heshaam Faili; | arxiv-cs.CL | 2020-03-24 |
| 260 | Stanza: A Python Natural Language Processing Toolkit For Many Human Languages IF:4 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce Stanza, an open-source Python natural language processing toolkit supporting 66 human languages. |
Peng Qi; Yuhao Zhang; Yuhui Zhang; Jason Bolton; Christopher D. Manning; | arxiv-cs.CL | 2020-03-16 |
| 261 | Hybrid Attention-Based Transformer Block Model For Distant Supervision Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a new framework using hybrid attention-based Transformer block with multi-instance learning to perform the DSRE task. |
Yan Xiao; Yaochu Jin; Ran Cheng; Kuangrong Hao; | arxiv-cs.CL | 2020-03-10 |
| 262 | Distributional Semantic Modeling: A Revised Technique To Train Term/word Vector Space Models Applying The Ontology-related Approach IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We design a new technique for the distributional semantic modeling with a neural network-based approach to learn distributed term representations (or term embeddings) – term vector space models as a result, inspired by the recent ontology-related approach (using different types of contextual knowledge such as syntactic knowledge, terminological knowledge, semantic knowledge, etc.) to the identification of terms (term extraction) and relations between them (relation extraction) called semantic pre-processing technology – SPT. |
Oleksandr Palagin; Vitalii Velychko; Kyrylo Malakhov; Oleksandr Shchurov; | arxiv-cs.CL | 2020-03-06 |
| 263 | Unsupervised Adversarial Domain Adaptation For Implicit Discourse Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an unsupervised adversarial domain adaptive network equipped with a reconstruction component. |
Hsin-Ping Huang; Junyi Jessy Li; | arxiv-cs.CL | 2020-03-04 |
| 264 | KEML: A Knowledge-Enriched Meta-Learning Framework For Lexical Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose the Knowledge-Enriched Meta-Learning (KEML) framework to address the task of lexical relation classification. |
Chengyu Wang; Minghui Qiu; Jun Huang; Xiaofeng He; | arxiv-cs.CL | 2020-02-25 |
| 265 | Unique Chinese Linguistic Phenomena IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Linguistics holds unique characteristics of generality, stability, and nationality, which will affect the formulation of extraction strategies and should be incorporated into the … |
Shengbin Jia; | arxiv-cs.CL | 2020-02-23 |
| 266 | Neural Relation Prediction For Simple Question Answering Over Knowledge Graph IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an instance-based method to capture the underlying relation of question and to this aim, we detect matching paraphrases of a new question which share the same relation, and their corresponding relation is selected as our prediction. |
Amin Abolghasemi; Saeedeh Momtazi; | arxiv-cs.CL | 2020-02-18 |
| 267 | Deeper Task-Specificity Improves Joint Entity And Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In particular, we introduce additional task-specific bidirectional RNN layers for both the NER and RE tasks and tune the number of shared and task-specific layers separately for different datasets. |
Phil Crone; | arxiv-cs.CL | 2020-02-15 |
| 268 | Neural Snowball For Few-Shot Relation Learning IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address new relations with few-shot instances, we propose a novel bootstrapping approach, Neural Snowball, to learn new relations by transferring semantic knowledge about existing relations. |
TIANYU GAO et. al. | aaai | 2020-02-07 |
| 269 | Self-Attention Enhanced Selective Gate With Entity-Aware Embedding For Distantly Supervised Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a brand-new light-weight neural framework to address the distantly supervised relation extraction problem and alleviate the defects in previous selective attention framework. |
YANG LI et. al. | aaai | 2020-02-07 |
| 270 | Multi-View Consistency For Relation Extraction Via Mutual Information And Structure Prediction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to overcome this issue, we introduce a novel method for RE that simultaneously induces the structures and predicts the relations for the input sentences, thus avoiding the external parsers and potentially leading to better sentence structures for RE. |
Amir Veyseh; Franck Dernoncourt; My Thai; Dejing Dou; Thien Nguyen; | aaai | 2020-02-07 |
| 271 | Improving Neural Relation Extraction With Positive And Unlabeled Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel approach to improve the performance of distant supervision relation extraction with Positive and Unlabeled (PU) Learning. |
ZHENGQIU HE et. al. | aaai | 2020-02-07 |
| 272 | Integrating Deep Learning With Logic Fusion For Information Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To combine such logic reasoning capabilities with learning capabilities of deep neural networks, we propose to integrate logical knowledge in the form of first-order logic into a deep learning system, which can be trained jointly in an end-to-end manner. |
Wenya Wang; Sinno Jialin Pan; | aaai | 2020-02-07 |
| 273 | Distilling Knowledge From Well-Informed Soft Labels For Neural Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to explore the supervision with soft labels in relation extraction, which makes it possible to integrate prior knowledge. |
ZHENYU ZHANG et. al. | aaai | 2020-02-07 |
| 274 | Localize, Assemble, And Predicate: Contextual Object Proposal Embedding For Visual Relation Detection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this problem, we propose localize-assemble-predicate network (LAP-Net), which decomposes VRD into three sub-tasks: localizing individual objects, assembling and predicting the subject-object pairs. |
Ruihai Wu; Kehan Xu; Chenchen Liu; Nan Zhuang; Yadong Mu; | aaai | 2020-02-07 |
| 275 | One-Shot Learning For Long-Tail Visual Relation Detection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: With this in mind, we designed a novel model for visual relation detection that works in one-shot settings. |
WEITAO WANG et. al. | aaai | 2020-02-07 |
| 276 | Effective Modeling Of Encoder-Decoder Architecture For Joint Entity And Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose two approaches to use encoder-decoder architecture for jointly extracting entities and relations. |
Tapas Nayak; Hwee Tou Ng; | aaai | 2020-02-07 |
| 277 | Integrating Relation Constraints With Neural Relation Extractors IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a unified framework to integrate relation constraints with NNs by introducing a new loss term, Constraint Loss. |
Yuan Ye; Yansong Feng; Bingfeng Luo; Yuxuan Lai; Dongyan Zhao; | aaai | 2020-02-07 |
| 278 | Are Noisy Sentences Useless For Distant Supervised Relation Extraction? IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, in this paper, we propose a novel method for distant supervised relation extraction, which employs unsupervised deep clustering to generate reliable labels for noisy sentences. |
Yuming Shang; He-Yan Huang; Xian-Ling Mao; Xin Sun; Wei Wei; | aaai | 2020-02-07 |
| 279 | Relation Extraction With Convolutional Network Over Learnable Syntax-Transport Graph IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we learn to transform the dependency tree into a weighted graph by considering the syntax dependencies of the connected nodes and persisting the structure of the original dependency tree. |
Kai Sun; Richong Zhang; Yongyi Mao; Samuel Mensah; Xudong Liu; | aaai | 2020-02-07 |
| 280 | Relation Extraction Exploiting Full Dependency Forests IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose to leverage full dependency forests for this task, where a full dependency forest encodes all possible trees. |
LIFENG JIN et. al. | aaai | 2020-02-07 |
| 281 | Joint Entity And Relation Extraction With A Hybrid Transformer And Reinforcement Learning Based Model IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a hybrid deep neural network model to jointly extract the entities and relations, and the model is also capable of filtering noisy data. |
Ya Xiao; Chengxiang Tan; Zhijie Fan; Qian Xu; Wenye Zhu; | aaai | 2020-02-07 |
| 282 | Simultaneously Linking Entities And Extracting Relations From Biomedical Text Without Mention-Level Supervision IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Instead, we propose a model which is trained to simultaneously produce entity linking and relation decisions while requiring no mention-level annotations. |
Trapit Bansal; Pat Verga; Neha Choudhary; Andrew McCallum; | aaai | 2020-02-07 |
| 283 | K-Adapter: Infusing Knowledge Into Pre-Trained Models With Adapters IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this, we propose K-Adapter, a framework that retains the original parameters of the pre-trained model fixed and supports the development of versatile knowledge-infused model. |
RUIZE WANG et. al. | arxiv-cs.CL | 2020-02-05 |
| 284 | A Neural Architecture For Person Ontology Population IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present a system for automatically populating a person ontology graph from unstructured data using neural models for Entity Classification and Relation Extraction. We introduce a new dataset for these tasks and discuss our results. |
Balaji Ganesan; Riddhiman Dasgupta; Akshay Parekh; Hima Patel; Berthold Reinwald; | arxiv-cs.AI | 2020-01-22 |
| 285 | BiOnt: Deep Learning Using Multiple Biomedical Ontologies For Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Successful biomedical relation extraction can provide evidence to researchers and clinicians about possible unknown associations between biomedical entities, advancing the current … |
Diana Sousa; Francisco M. Couto; | arxiv-cs.IR | 2020-01-20 |
| 286 | A Logic-based Relational Learning Approach To Relation Extraction: The OntoILPER System IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we present OntoILPER, a logic-based relational learning approach to Relation Extraction that uses Inductive Logic Programming for generating extraction models in the form of symbolic extraction rules. |
Rinaldo Lima; Bernard Espinasse; Fred Freitas; | arxiv-cs.AI | 2020-01-13 |
| 287 | A Neural Approach To Discourse Relation Signal Detection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we present a data-driven approach to signal detection using a distantly supervised neural network and develop a metric, Delta s (or ‘delta-softmax’), to quantify signaling strength. |
Amir Zeldes; Yang Liu; | arxiv-cs.CL | 2020-01-08 |
| 288 | Chemical-induced Disease Relation Extraction With Dependency Information And Prior Knowledge IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel convolutional attention network (CAN) for CDR extraction. |
HUIWEI ZHOU et. al. | arxiv-cs.CL | 2020-01-01 |
| 289 | Knowledge-guided Convolutional Networks For Chemical-Disease Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Results: This paper proposes a novel model called Knowledge-guided Convolutional Networks (KCN) to leverage prior knowledge for CDR extraction. |
HUIWEI ZHOU et. al. | arxiv-cs.CL | 2019-12-22 |
| 290 | Combining Context And Knowledge Representations For Chemical-Disease Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a neural network-based attention model (NAM) for CDR extraction, which makes full use of context information in documents and prior knowledge in KBs. |
HUIWEI ZHOU et. al. | arxiv-cs.CL | 2019-12-22 |
| 291 | Learning From Explanations With Neural Module Execution Tree IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel Neural Modular Execution Tree (NMET) framework for augmenting sequence classification with NL explanations. |
YUJIA QIN et. al. | iclr | 2019-12-21 |
| 292 | The Performance Evaluation Of Multi-representation In The Deep Learning Models For Relation Extraction Task IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work addresses the question of how is improved the relation extraction using different types of representations generated by pretrained language representation models. |
Jefferson A. Peña Torres; Raul Ernesto Gutierrez; Victor A. Bucheli; Fabio A. Gonzalez O; | arxiv-cs.CL | 2019-12-17 |
| 293 | Effective Attention Modeling For Neural Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a novel and effective attention model which incorporates syntactic information of the sentence and a multi-factor attention mechanism. |
Tapas Nayak; Hwee Tou Ng; | arxiv-cs.CL | 2019-12-08 |
| 294 | Cooperative Reasoning On Knowledge Graph And Corpus: A Multi-agentReinforcement Learning Approach IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a model that leverages the text corpus to cure such limitations, either the explicit or implicit missing links. |
Yunan Zhang; Xiang Cheng; Heting Gao; Chengxiang Zhai; | arxiv-cs.CL | 2019-12-04 |
| 295 | Enhancing Relation Extraction Using Syntactic Indicators And Sentential Contexts IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To leverage both syntactic indicators and sentential contexts, we propose an indicator-aware approach for relation extraction. |
Qiongxing Tao; Xiangfeng Luo; Hao Wang; | arxiv-cs.CL | 2019-12-04 |
| 296 | Chemical-protein Interaction Extraction Via Gaussian Probability Distribution And External Biomedical Knowledge IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Results: In this paper, we propose a novel neural network-based approach to improve CPI extraction. |
CONG SUN et. al. | arxiv-cs.CL | 2019-11-21 |
| 297 | Are Noisy Sentences Useless For Distant Supervised Relation Extraction? IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Thus, in this paper, we propose a novel method for distant supervised relation extraction, which employs unsupervised deep clustering to generate reliable labels for noisy sentences. |
Yuming Shang; | arxiv-cs.CL | 2019-11-21 |
| 298 | Improving Distant Supervised Relation Extraction By Dynamic Neural Network IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to leverage this connection to improve the relation extraction accuracy. |
Yanjie Gou; Yinjie Lei; Lingqiao Liu; Pingping Zhang; Xi Peng; | arxiv-cs.CL | 2019-11-15 |
| 299 | Leveraging Dependency Forest For Neural Medical Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate a method to alleviate this problem by utilizing dependency forests. |
LINFENG SONG et. al. | arxiv-cs.CL | 2019-11-11 |
| 300 | Towards Understanding Gender Bias In Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We create WikiGenderBias, a distantly supervised dataset with a human annotated test set. |
ANDREW GAUT et. al. | arxiv-cs.LG | 2019-11-09 |
| 301 | E-BERT: Efficient-Yet-Effective Entity Embeddings For BERT IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel way of injecting factual knowledge about entities into the pretrained BERT model (Devlin et al., 2019): We align Wikipedia2Vec entity vectors (Yamada et al., 2016) with BERT’s native wordpiece vector space and use the aligned entity vectors as if they were wordpiece vectors. |
Nina Poerner; Ulli Waltinger; Hinrich Schütze; | arxiv-cs.CL | 2019-11-09 |
| 302 | Relation Adversarial Network For Low Resource Knowledge Graph Completion IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we aim at predicting new facts under a challenging setting where only limited training instances are available. |
NINGYU ZHANG et. al. | arxiv-cs.CL | 2019-11-08 |
| 303 | Neural Graph Embedding Methods For Natural Language Processing IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In the first part of the thesis, we propose three solutions to alleviate this problem: (1) KG Canonicalization, i.e., identifying and merging duplicate entities in a KG, (2) Relation Extraction which involves automating the process of extracting semantic relationships between entities from unstructured text, and (3) Link prediction which includes inferring missing facts based on the known facts in a KG. |
Shikhar Vashishth; | arxiv-cs.CL | 2019-11-07 |
| 304 | Learning From Explanations With Neural Execution Tree IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel Neural Execution Tree (NExT) framework to augment training data for text classification using NL explanations. |
ZIQI WANG et. al. | arxiv-cs.CL | 2019-11-04 |
| 305 | On The Effectiveness Of The Pooling Methods For Biomedical Relation Extraction With Deep Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to answer this question, in this work, we conduct a comprehensive study to evaluate the effectiveness of different pooling mechanisms for the deep learning models in biomedical RE. |
Tuan Ngo Nguyen; Franck Dernoncourt; Thien Huu Nguyen; | arxiv-cs.CL | 2019-11-04 |
| 306 | Enriching Pre-trained Language Model With Entity Information For Relation Classification IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a model that both leverages the pre-trained BERT language model and incorporates information from the target entities to tackle the relation classification task. |
Shanchan Wu; Yifan He; | cikm | 2019-11-03 |
| 307 | A Fine-grained And Noise-aware Method For Neural Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these problems, we propose two reasonable assumptions and craft reinforcement learning to capture the expressive sentence for each relation mentioned in a bag. |
Jianfeng Qu; Wen Hua; Dantong Ouyang; Xiaofang Zhou; Ximing Li; | cikm | 2019-11-03 |
| 308 | Nested Relation Extraction With Iterative Neural Network IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we formally formulate the nested relation extraction problem, and come up with a solution using Iterative Neural Network. |
Yixuan Cao; Dian Chen; Hongwei Li; Ping Luo; | cikm | 2019-11-03 |
| 309 | Large Margin Prototypical Network For Few-shot Relation Classification With Fine-grained Features IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider few-shot learning is of great practical significance to RC and thus improve a modern framework of metric learning for few-shot RC. |
Miao Fan; Yeqi Bai; Mingming Sun; Ping Li; | cikm | 2019-11-03 |
| 310 | Entity, Relation, And Event Extraction With Contextualized Span Representations IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. |
David Wadden; Ulme Wennberg; Yi Luan; Hannaneh Hajishirzi; | emnlp | 2019-11-02 |
| 311 | FewRel 2.0: Towards More Challenging Few-Shot Relation Classification IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present FewRel 2.0, a more challenging task to investigate two aspects of few-shot relation classification models: (1) Can they adapt to a new domain with only a handful of instances? |
TIANYU GAO et. al. | emnlp | 2019-11-02 |
| 312 | KnowledgeNet: A Benchmark Dataset For Knowledge Base Population IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: KnowledgeNet is a benchmark dataset for the task of automatically populating a knowledge base (Wikidata) with facts expressed in natural language text on the web. |
Filipe Mesquita; Matteo Cannaviccio; Jordan Schmidek; Paramita Mirza; Denilson Barbosa; | emnlp | 2019-11-02 |
| 313 | Open Relation Extraction: Relational Knowledge Transfer From Supervised Data To Unsupervised Data IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose Relational Siamese Networks (RSNs) to learn similarity metrics of relations from labeled data of pre-defined relations, and then transfer the relational knowledge to identify novel relations in unlabeled data. |
RUIDONG WU et. al. | emnlp | 2019-11-02 |
| 314 | Connecting The Dots: Document-level Neural Relation Extraction With Edge-oriented Graphs IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We thus propose an edge-oriented graph neural model for document-level relation extraction. |
Fenia Christopoulou; Makoto Miwa; Sophia Ananiadou; | emnlp | 2019-11-02 |
| 315 | Improving Distantly-Supervised Relation Extraction With Joint Label Embedding IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel multi-layer attention-based model to improve relation extraction with joint label embedding. |
LINMEI HU et. al. | emnlp | 2019-11-02 |
| 316 | Cross-lingual Structure Transfer For Relation And Event Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We investigate the suitability of cross-lingual structure transfer techniques for these tasks. |
ANANYA SUBBURATHINAM et. al. | emnlp | 2019-11-02 |
| 317 | An Improved Neural Baseline For Temporal Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper proposes a new neural system that achieves about 10% absolute improvement in accuracy over the previous best system (25% error reduction) on two benchmark datasets. |
Qiang Ning; Sanjay Subramanian; Dan Roth; | emnlp | 2019-11-02 |
| 318 | Self-Attention Enhanced CNNs And Collaborative Curriculum Learning For Distantly Supervised Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel model that employs a collaborative curriculum learning framework to reduce the effects of mislabelled data. |
Yuyun Huang; Jinhua Du; | emnlp | 2019-11-02 |
| 319 | Easy First Relation Extraction With Information Redundancy IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an easy first approach for relation extraction with information redundancies, embedded in the results produced by local sentence level extractors, during which conflict decisions are resolved with domain and uniqueness constraints. |
Shuai Ma; Gang Wang; Yansong Feng; Jinpeng Huai; | emnlp | 2019-11-02 |
| 320 | Neural Cross-Lingual Relation Extraction Based On Bilingual Word Embedding Mapping IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new approach for cross-lingual RE model transfer based on bilingual word embedding mapping. |
Jian Ni; Radu Florian; | emnlp | 2019-11-02 |
| 321 | Leveraging 2-hop Distant Supervision From Table Entity Pairs For Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we introduce a new strategy named 2-hop DS to enhance distantly supervised RE, based on the observation that there exist a large number of relational tables on the Web which contain entity pairs that share common relations. |
xiang deng; Huan Sun; | emnlp | 2019-11-02 |
| 322 | Uncover The Ground-Truth Relations In Distant Supervision: A Neural Expectation-Maximization Framework IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To cope with this challenge, we propose a novel label-denoising framework that combines neural network with probabilistic modelling, which naturally takes into account the noisy labels during learning. |
Junfan Chen; Richong Zhang; Yongyi Mao; Hongyu Guo; Jie Xu; | emnlp | 2019-11-02 |
| 323 | Nearly-Unsupervised Hashcode Representations For Biomedical Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to optimize the hashcode representations in a nearly unsupervised manner, in which we only use data points, but not their class labels, for learning. |
Sahil Garg; Aram Galstyan; Greg Ver Steeg; Guillermo Cecchi; | emnlp | 2019-11-02 |
| 324 | Towards Extracting Medical Family History From Natural Language Interactions: A New Dataset And Baselines IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a new dataset consisting of natural language interactions annotated with medical family histories, obtained during interactions with a genetic counselor and through crowdsourcing, following a questionnaire created by experts in the domain. |
Mahmoud Azab; Stephane Dadian; Vivi Nastase; Larry An; Rada Mihalcea; | emnlp | 2019-11-02 |
| 325 | Rewarding Coreference Resolvers For Being Consistent With World Knowledge IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show how to improve coreference resolvers by forwarding their input to a relation extraction system and reward the resolvers for producing triples that are found in knowledge bases. |
RAHUL ARALIKATTE et. al. | emnlp | 2019-11-02 |
| 326 | Cross-Sentence N-ary Relation Extraction Using Lower-Arity Universal Schemas IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel approach to cross-sentence n-ary relation extraction based on universal schemas. |
Kosuke Akimoto; Takuya Hiraoka; Kunihiko Sadamasa; Mathias Niepert; | emnlp | 2019-11-02 |
| 327 | Learning To Infer Entities, Properties And Their Relations From Clinical Conversations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We extend the SAT model to jointly infer not only entities and their properties but also relations between them. |
Nan Du; Mingqiu Wang; Linh Tran; Gang Lee; Izhak Shafran; | emnlp | 2019-11-02 |
| 328 | Learning The Extraction Order Of Multiple Relational Facts In A Sentence With Reinforcement Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we argue that the extraction order is important in this task. |
XIANGRONG ZENG et. al. | emnlp | 2019-11-02 |
| 329 | Next Sentence Prediction Helps Implicit Discourse Relation Classification Within And Across Domains IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We here show that this shortcoming can be effectively addressed by using the bidirectional encoder representation from transformers (BERT) proposed by Devlin et al. (2019), which were trained on a next-sentence prediction task, and thus encode a representation of likely next sentences. |
Wei Shi; Vera Demberg; | emnlp | 2019-11-02 |
| 330 | Looking Beyond Label Noise: Shifted Label Distribution Matters In Distantly Supervised Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we study the problem what limits the performance of DS-trained neural models, conduct thorough analyses, and identify a factor that can influence the performance greatly, shifted label distribution. |
Qinyuan Ye; Liyuan Liu; Maosen Zhang; Xiang Ren; | emnlp | 2019-11-02 |
| 331 | Weakly Supervised Cross-lingual Semantic Relation Classification Via Knowledge Distillation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a cross-lingual relation classifier trained only with English examples and a bilingual dictionary. |
Yogarshi Vyas; Marine Carpuat; | emnlp | 2019-11-02 |
| 332 | Deep Bidirectional Transformers For Relation Extraction Without Supervision IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel framework to deal with relation extraction tasks in cases where there is complete lack of supervision, either in the form of gold annotations, or relations from a knowledge base. |
Yannis Papanikolaou; Ian Roberts; Andrea Pierleoni; | arxiv-cs.LG | 2019-11-01 |
| 333 | Attention-Gated Graph Convolutions For Extracting Drug Interaction Information From Drug Labels IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this study, we tackle the problem of jointly extracting drugs and their interactions, including interaction outcome, from drug labels. |
Tung Tran; Ramakanth Kavuluru; Halil Kilicoglu; | arxiv-cs.CL | 2019-10-27 |
| 334 | A Survey On Recent Advances In Named Entity Recognition From Deep Learning Models IF:4 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a comprehensive survey of deep neural network architectures for NER, and contrast them with previous approaches to NER based on feature engineering and other supervised or semi-supervised learning algorithms. |
Vikas Yadav; Steven Bethard; | arxiv-cs.CL | 2019-10-24 |
| 335 | Pose-Aware Multi-Level Feature Network For Human Object Interaction Detection IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address those challenges, we propose a multi-level relation detection strategy that utilizes human pose cues to capture global spatial configurations of relations and as an attention mechanism to dynamically zoom into relevant regions at human part level. |
Bo Wan; Desen Zhou; Yongfei Liu; Rongjie Li; Xuming He; | iccv | 2019-10-24 |
| 336 | Semantic Graph Convolutional Network For Implicit Discourse Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel and effective Semantic Graph Convolutional Network (SGCN) to enhance the modeling of inter-argument semantics on a deeper interaction level for implicit discourse relation classification. |
YINGXUE ZHANG et. al. | arxiv-cs.CL | 2019-10-21 |
| 337 | HiExpan: Task-Guided Taxonomy Construction By Hierarchical Tree Expansion IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to construct a task-guided taxonomy from a domain-specific corpus and allow users to input a seed taxonomy, serving as the task guidance. |
JIAMING SHEN et. al. | arxiv-cs.CL | 2019-10-17 |
| 338 | Learning High-order Structural And Attribute Information By Knowledge Graph Attention Networks For Enhancing Knowledge Graph Embedding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome these limitations, this paper propose a novel knowledge graph embedding method, named KANE, which is inspired by the recent developments of graph convolutional networks (GCN). |
WENQIANG LIU et. al. | arxiv-cs.AI | 2019-10-09 |
| 339 | Linguistically Informed Relation Extraction And Neural Architectures For Nested Named Entity Recognition In BioNLP-OST 2019 IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents our findings from participating in BioNLP Shared Tasks 2019. |
Usama Yaseen; Pankaj Gupta; Hinrich Schütze; | arxiv-cs.CL | 2019-10-08 |
| 340 | Improving Relation Extraction With Knowledge-attention IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel knowledge-attention encoder which incorporates prior knowledge from external lexical resources into deep neural networks for relation extraction task. |
Pengfei Li; Kezhi Mao; Xuefeng Yang; Qi Li; | arxiv-cs.CL | 2019-10-07 |
| 341 | Extracting UMLS Concepts From Medical Text Using General And Domain-Specific Deep Learning Models IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We contrast our results against the well-known i2b2 2010 entity recognition dataset, and propose a new method to combine general and domain-specific information. |
KATHLEEN C. FRASER et. al. | arxiv-cs.CL | 2019-10-02 |
| 342 | Type-aware Convolutional Neural Networks For Slot Filling IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we focus on the relation classification component of a slot filling system. |
Heike Adel; Hinrich Schütze; | arxiv-cs.CL | 2019-10-01 |
| 343 | OpenNRE: An Open And Extensible Toolkit For Neural Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: OpenNRE is an open-source and extensible toolkit that provides a unified framework to implement neural models for relation extraction (RE). |
XU HAN et. al. | arxiv-cs.CL | 2019-09-28 |
| 344 | Fine-tune Bert For DocRED With Two-step Process IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We argue that such simple baselines are not strong enough to model to complex interaction between entities. |
Hong Wang; Christfried Focke; Rob Sylvester; Nilesh Mishra; William Wang; | arxiv-cs.CL | 2019-09-26 |
| 345 | Biomedical Relation Extraction With Pre-trained Language Representations And Minimal Task-specific Architecture IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents our participation in the AGAC Track from the 2019 BioNLP Open Shared Tasks. |
Ashok Thillaisundaram; Theodosia Togia; | arxiv-cs.CL | 2019-09-26 |
| 346 | Deep Structured Neural Network For Event Temporal Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel deep structured learning framework for event temporal relation extraction. |
RUJUN HAN et. al. | arxiv-cs.CL | 2019-09-22 |
| 347 | Dependency-based Text Graphs For Keyphrase And Summary Extraction With Applications To Interactive Content Retrieval IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We build a bridge between neural network-based machine learning and graph-based natural language processing and introduce a unified approach to keyphrase, summary and relation extraction by aggregating dependency graphs from links provided by a deep-learning based dependency parser. |
Paul Tarau; Eduardo Blanco; | arxiv-cs.AI | 2019-09-20 |
| 348 | Argumentative Relation Classification As Plausibility Ranking IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To this aim, we propose a simple reconstruction trick which enables us to build minimal pairs of plausible and implausible texts by simulating natural contexts in which two argumentative units are likely or unlikely to appear. |
Juri Opitz; | arxiv-cs.CL | 2019-09-19 |
| 349 | Triplet-Aware Scene Graph Embeddings IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we train scene graph embeddings in a layout generation task with different forms of supervision, specifically introducing triplet super-vision and data augmentation. |
Brigit Schroeder; Subarna Tripathi; Hanlin Tang; | arxiv-cs.CV | 2019-09-19 |
| 350 | Span-based Joint Entity And Relation Extraction With Transformer Pre-training IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce SpERT, an attention model for span-based joint entity and relation extraction. |
Markus Eberts; Adrian Ulges; | arxiv-cs.CL | 2019-09-17 |
| 351 | Neural Correction Model For Open-Domain Named Entity Recognition IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the low RAT problem of previous datasets, we introduce a multi-task learning method to exploit the context information. In this way, we build a large and high-quality dataset called AnchorNER and then train various models with it. |
MENGDI ZHU et. al. | arxiv-cs.CL | 2019-09-13 |
| 352 | Taxonomical Hierarchy Of Canonicalized Relations From Multiple Knowledge Bases IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This work addresses two important questions pertinent to Relation Extraction (RE). |
Akshay Parekh; Ashish Anand; Amit Awekar; | arxiv-cs.CL | 2019-09-13 |
| 353 | Global Locality In Biomedical Relation And Event Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose an approach to both relation and event extraction, for simultaneously predicting relationships between all mention pairs in a text. |
Elaheh ShafieiBavani; Antonio Jimeno Yepes; Xu Zhong; David Martinez Iraola; | arxiv-cs.CL | 2019-09-10 |
| 354 | Nearly-Unsupervised Hashcode Representations For Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose to optimize the hashcode representations in a nearly unsupervised manner, in which we only use data points, but not their class labels, for learning. |
Sahil Garg; Aram Galstyan; Greg Ver Steeg; Guillermo Cecchi; | arxiv-cs.LG | 2019-09-09 |
| 355 | Specializing Unsupervised Pretraining Models For Word-Level Semantic Similarity IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we complement such distributional knowledge with external lexical knowledge, that is, we integrate the discrete knowledge on word-level semantic similarity into pretraining. |
Anne Lauscher; Ivan Vulić; Edoardo Maria Ponti; Anna Korhonen; Goran Glavaš; | arxiv-cs.CL | 2019-09-05 |
| 356 | Rewarding Coreference Resolvers For Being Consistent With World Knowledge IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We show how to improve coreference resolvers by forwarding their input to a relation extraction system and reward the resolvers for producing triples that are found in knowledge bases. |
RAHUL ARALIKATTE et. al. | arxiv-cs.CL | 2019-09-05 |
| 357 | Joint Event And Temporal Relation Extraction With Shared Representations And Structured Prediction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a joint event and temporal relation extraction model with shared representation learning and structured prediction. |
Rujun Han; Qiang Ning; Nanyun Peng; | arxiv-cs.CL | 2019-09-02 |
| 358 | Learning To Infer Entities, Properties And Their Relations From Clinical Conversations IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Recently we proposed the Span Attribute Tagging (SAT) Model (Du et al., 2019) to infer clinical entities (e.g., symptoms) and their properties (e.g., duration). |
Nan Du; Mingqiu Wang; Linh Tran; Gang Li; Izhak Shafran; | arxiv-cs.CL | 2019-08-30 |
| 359 | Temporal Reasoning Graph For Activity Recognition IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose an efficient temporal reasoning graph (TRG) to simultaneously capture the appearance features and temporal relation between video sequences at multiple time scales. |
Jingran Zhang; Fumin Shen; Xing Xu; Heng Tao Shen; | arxiv-cs.CV | 2019-08-26 |
| 360 | Joint Extraction Of Entities And Relations With A Hierarchical Multi-task Tagging Model IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a hierarchical multi-task tagging model, called HMT, which captures such interdependency and achieves better performance for joint extraction of entities and relations. |
ZHEPEI WEI et. al. | arxiv-cs.CL | 2019-08-23 |
| 361 | Transfer Learning For Relation Extraction Via Relation-Gated Adversarial Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To solve these problems, we propose a novel model of relation-gated adversarial learning for relation extraction, which extends the adversarial based domain adaptation. |
NINGYU ZHANG et. al. | arxiv-cs.LG | 2019-08-22 |
| 362 | Fine-tuning BERT For Joint Entity And Relation Extraction In Chinese Medical Text IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a focused attention model for the joint entity and relation extraction task. |
KUI XUE et. al. | arxiv-cs.CL | 2019-08-21 |
| 363 | Populating Web Scale Knowledge Graphs Using Distantly Supervised Relation Extraction And Validation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a fully automated system to extend knowledge graphs using external information from web-scale corpora. |
Sarthak Dash; Michael R. Glass; Alfio Gliozzo; Mustafa Canim; | arxiv-cs.CL | 2019-08-21 |
| 364 | Fine-grained Sentiment Analysis With Faithful Attention IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Surprisingly, we found that despite reasonable performance, the model’s attention was often systematically misaligned with the words that contribute to sentiment. |
Ruiqi Zhong; Steven Shao; Kathleen McKeown; | arxiv-cs.CL | 2019-08-19 |
| 365 | Few-shot Text Classification With Distributional Signatures IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore meta-learning for few-shot text classification. |
Yujia Bao; Menghua Wu; Shiyu Chang; Regina Barzilay; | arxiv-cs.CL | 2019-08-16 |
| 366 | BERT-Based Multi-Head Selection For Joint Entity-Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we report our method for the Information Extraction task in 2019 Language and Intelligence Challenge. Second, we introduce a large-scale Baidu Baike corpus for entity recognition pre-training, which is of weekly supervised learning since there is no actual named entity label. |
Weipeng Huang; Xingyi Cheng; Taifeng Wang; Wei Chu; | arxiv-cs.CL | 2019-08-16 |
| 367 | X-WikiRE: A Large, Multilingual Resource For Relation Extraction As Machine Comprehension IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Exploiting this, we introduce a new multilingual dataset (X-WikiRE), framing relation extraction as a multilingual machine reading problem. |
Mostafa Abdou; Cezar Sas; Rahul Aralikatte; Isabelle Augenstein; Anders Søgaard; | arxiv-cs.CL | 2019-08-14 |
| 368 | Understanding Spatial Language In Radiology: Representation Framework, Annotation, And Spatial Relation Extraction From Chest X-ray Reports Using Deep Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: For this, we propose a deep learning-based natural language processing (NLP) method involving both word and character-level encodings. |
SURABHI DATTA et. al. | arxiv-cs.CL | 2019-08-13 |
| 369 | Beyond Word Attention: Using Segment Attention In Neural Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we aim to incorporate such segment information into neural relation extractor. |
BOWEN YU et. al. | ijcai | 2019-08-09 |
| 370 | Relation Extraction Using Supervision From Topic Knowledge Of Relation Labels IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we mine the topic knowledge of a relation to explicitly represent the semantics of this relation, and model relation extraction as a matching problem. |
HAIYUN JIANG et. al. | ijcai | 2019-08-09 |
| 371 | Improving Cross-Domain Performance For Relation Extraction Via Dependency Prediction And Information Flow Control IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a novel method to use dependency trees in RE for deep learning models that jointly predicts dependency and semantics relations. |
Amir Pouran Ben Veyseh; Thien Nguyen; Dejing Dou; | ijcai | 2019-08-09 |
| 372 | Relation Extraction Via Domain-aware Transfer Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel approach called, Relation Extraction via Domain-aware Transfer Learning (ReTrans), to extract relation mentions from a given text corpus by exploring the experience from a large amount of existing KBs which may not be closely related to the target relation. |
Shimin Di; Yanyan Shen; Lei Chen; | kdd | 2019-08-01 |
| 373 | Zero-shot Transfer For Implicit Discourse Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a new system using zero-shot transfer learning for implicit discourse relation classification, where the only resource used for the target language is unannotated parallel text. |
Murathan Kurfalı; Robert Östling; | arxiv-cs.CL | 2019-07-30 |
| 374 | Matching The Blanks: Distributional Similarity For Relation Learning IF:4 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we build on extensions of Harris’ distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. |
Livio Baldini Soares; Nicholas FitzGerald; Jeffrey Ling; Tom Kwiatkowski,; | acl | 2019-07-28 |
| 375 | Attention Guided Graph Convolutional Networks For Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Attention Guided Graph Convolutional Networks (AGGCNs), a novel model which directly takes full dependency trees as inputs. |
Zhijiang Guo; Yan Zhang; Wei Lu,; | acl | 2019-07-28 |
| 376 | Entity-Relation Extraction As Multi-Turn Question Answering IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new paradigm for the task of entity-relation extraction. |
XIAOYA LI et. al. | acl | 2019-07-28 |
| 377 | GraphRel: Modeling Text As Relational Graphs For Joint Entity And Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present GraphRel, an end-to-end relation extraction model which uses graph convolutional networks (GCNs) to jointly learn named entities and relations. |
Tsu-Jui Fu; Peng-Hsuan Li; Wei-Yun Ma,; | acl | 2019-07-28 |
| 378 | Neural Relation Extraction For Knowledge Base Enrichment IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This way, NED errors may cause extraction errors that affect the overall precision and recall.To address this problem, we propose an end-to-end relation extraction model for KB enrichment based on a neural encoder-decoder model. |
Bayu Distiawan Trisedya; Gerhard Weikum; Jianzhong Qi; Rui Zhang,; | acl | 2019-07-28 |
| 379 | ARNOR: Attention Regularization Based Noise Reduction For Distant Supervision Relation Classification IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose ARNOR, a novel Attention Regularization based NOise Reduction framework for distant supervision relation classification. |
Wei Jia; Dai Dai; Xinyan Xiao; Hua Wu,; | acl | 2019-07-28 |
| 380 | DocRED: A Large-Scale Document-Level Relation Extraction Dataset IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to acceleratethe research on document-level RE, we in-troduce DocRED, a new dataset constructedfrom Wikipedia and Wikidata with three features: (1) DocRED annotates both named entities and relations, and is the largest human-annotated dataset for document-level RE fromplain text; (2) DocRED requires reading multiple sentences in a document to extract entities and infer their relations by synthesizing all information of the document; (3) alongwith the human-annotated data, we also offer large-scale distantly supervised data, whichenables DocRED to be adopted for both supervised and weakly supervised scenarios. |
YUAN YAO et. al. | acl | 2019-07-28 |
| 381 | Fine-Grained Temporal Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel semantic framework for modeling temporal relations and event durations that maps pairs of events to real-valued scales. |
Siddharth Vashishtha; Benjamin Van Durme; Aaron Steven White,; | acl | 2019-07-28 |
| 382 | Inter-sentence Relation Extraction With Document-level Graph Convolutional Neural Network IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel inter-sentence relation extraction model that builds a labelled edge graph convolutional neural network model on a document-level graph. |
Sunil Kumar Sahu; Fenia Christopoulou; Makoto Miwa; Sophia Ananiadou,; | acl | 2019-07-28 |
| 383 | Chinese Relation Extraction With Multi-Grained Information And External Linguistic Knowledge IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address the issues, we propose a multi-grained lattice framework (MG lattice) for Chinese relation extraction to take advantage of multi-grained language information and external linguistic knowledge. |
Ziran Li; Ning Ding; Zhiyuan Liu; Haitao Zheng; Ying Shen,; | acl | 2019-07-28 |
| 384 | Model-Agnostic Meta-Learning For Relation Classification With Limited Supervision IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper we frame the task of supervised relation classification as an instance of meta-learning. |
Abiola Obamuyide; Andreas Vlachos,; | acl | 2019-07-28 |
| 385 | Multi-Level Matching And Aggregation Network For Few-Shot Relation Classification IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a multi-level matching and aggregation network (MLMAN) for few-shot relation classification. |
Zhi-Xiu Ye; Zhen-Hua Ling,; | acl | 2019-07-28 |
| 386 | Joint Type Inference On Entities And Relations Via Graph Convolutional Networks IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To tackle the joint type inference task, we propose a novel graph convolutional network (GCN) running on an entity-relation bipartite graph. |
CHANGZHI SUN et. al. | acl | 2019-07-28 |
| 387 | Fine-tuning Pre-Trained Transformer Language Models To Distantly Supervised Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this gap, we utilize a pre-trained language model, the OpenAI Generative Pre-trained Transformer (GPT) (Radford et al., 2018). |
Christoph Alt; Marc Hübner; Leonhard Hennig,; | acl | 2019-07-28 |
| 388 | Graph Neural Networks With Generated Parameters For Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel graph neural network with generated parameters (GP-GNNs). |
HAO ZHU et. al. | acl | 2019-07-28 |
| 389 | Span-Level Model For Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these concerns, we present a model which directly models all possible spans and performs joint entity mention detection and relation extraction. |
Kalpit Dixit; Yaser Al-Onaizan,; | acl | 2019-07-28 |
| 390 | Unsupervised Information Extraction: Regularizing Discriminative Approaches With Relation Distribution Losses IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To overcome this limitation, we introduce a skewness loss which encourages the classifier to predict a relation with confidence given a sentence, and a distribution distance loss enforcing that all relations are predicted in average. |
Étienne Simon; Vincent Guigue; Benjamin Piwowarski,; | acl | 2019-07-28 |
| 391 | Learning To Relate From Captions And Bounding Boxes IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel approach that predicts the relationships between various entities in an image in a weakly supervised manner by relying on image captions and object bounding box annotations as the sole source of supervision. |
Sarthak Garg; Joel Ruben Antony Moniz; Anshu Aviral; Priyatham Bollimpalli,; | acl | 2019-07-28 |
| 392 | Learning Representation Mapping For Relation Detection In Knowledge Base Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a simple mapping method, named representation adapter, to learn the representation mapping for both seen and unseen relations based on previously learned relation embedding. |
PENG WU et. al. | acl | 2019-07-28 |
| 393 | Exploiting Entity BIO Tag Embeddings And Multi-task Learning For Relation Extraction With Imbalanced Data IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate this problem, we propose a multi-task architecture which jointly trains a model to perform relation identification with cross-entropy loss and relation classification with ranking loss. |
WEI YE et. al. | acl | 2019-07-28 |
| 394 | Eliciting Knowledge From Experts: Automatic Transcript Parsing For Cognitive Task Analysis IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a weakly-supervised information extraction framework for automated CTA transcript parsing. |
Junyi Du; He Jiang; Jiaming Shen; Xiang Ren,; | acl | 2019-07-28 |
| 395 | DIAG-NRE: A Neural Pattern Diagnosis Framework For Distantly Supervised Neural Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To ease the labor-intensive workload of pattern writing and enable the quick generalization to new relation types, we propose a neural pattern diagnosis framework, DIAG-NRE, that can automatically summarize and refine high-quality relational patterns from noise data with human experts in the loop. |
SHUN ZHENG et. al. | acl | 2019-07-28 |
| 396 | Collocation Classification With Unsupervised Relation Vectors IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore to which extent the current distributional landscape based on word embeddings provides a suitable basis for classification of collocations, i.e., pairs of words between which idiosyncratic lexical relations hold. |
Luis Espinosa Anke; Steven Schockaert; Leo Wanner,; | acl | 2019-07-28 |
| 397 | Hybrid Neural Tagging Model For Open Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, to overcome these difficulties, we build a large-scale, high-quality training corpus in a fully automated way, and design a tagging scheme to assist in transforming the ORE task into a sequence tagging processing. |
Shengbin Jia; Yang Xiang; | arxiv-cs.CL | 2019-07-26 |
| 398 | SpanBERT: Improving Pre-training By Representing And Predicting Spans IF:6 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. |
MANDAR JOSHI et. al. | arxiv-cs.CL | 2019-07-24 |
| 399 | Harvesting Drug Effectiveness From Social Media IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a model regarding mention pairs as nodes connected by multiple types of edges. To this end, we build a dataset containing 25K tweets describing drug use, and further harvest drug effectiveness by performing Relation Extraction (RE) between chemicals and diseases. |
Zi Chai; Xiaojun Wan; Zhao Zhang; Minjie Li; | sigir | 2019-07-20 |
| 400 | Answer-enhanced Path-aware Relation Detection Over Knowledge Base IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a Knowledge-driven Relation Detection network (KRD) to interactively learn answer-enhanced question representations and path-aware relation representations for relation detection. |
Daoyuan Chen; Min Yang; Hai-Tao Zheng; Yaliang Li; Ying Shen; | sigir | 2019-07-20 |
| 401 | Identifying Entity Properties From Text With Zero-shot Learning IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a method for identifying a set of entity properties from text. |
Wiradee Imrattanatrai; Makoto P. Kato; Masatoshi Yoshikawa; | sigir | 2019-07-20 |
| 402 | Learning Representation Mapping For Relation Detection In Knowledge Base Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a simple mapping method, named representation adapter, to learn the representation mapping for both seen and unseen relations based on previously learned relation embedding. |
PENG WU et. al. | arxiv-cs.CL | 2019-07-17 |
| 403 | Tackling Graphical NLP Problems With Graph Recurrent Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this thesis, we propose a novel graph neural network, named graph recurrent network (GRN). |
Linfeng Song; | arxiv-cs.CL | 2019-07-13 |
| 404 | Improving Cross-Domain Performance For Relation Extraction Via Dependency Prediction And Information Flow Control IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper introduces a novel method to use dependency trees in RE for deep learning models that jointly predicts dependency and semantics relations. |
Amir Pouran Ben Veyseh; Thien Huu Nguyen; Dejing Dou; | arxiv-cs.CL | 2019-07-07 |
| 405 | Constructing Large Scale Biomedical Knowledge Bases From Scratch With Rapid Annotation Of Interpretable Patterns IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present a simple and effective method of extracting new facts with a pre-specified binary relationship type from the biomedical literature, without requiring any training data or hand-crafted rules. |
Julien Fauqueur; Ashok Thillaisundaram; Theodosia Togia; | arxiv-cs.CL | 2019-07-02 |
| 406 | CrowdGame: A Game-Based Crowdsourcing System For Cost-Effective Data Labeling IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents CrowdGame, a crowdsourcing system that harnesses the crowd to gather data labels in a cost-effective way. |
TONGYU LIU et. al. | sigmod | 2019-07-02 |
| 407 | Is Artificial Data Useful For Biomedical Natural Language Processing Algorithms? Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a generic methodology to guide the generation of clinical text with key phrases. |
Zixu Wang; Julia Ive; Sumithra Velupillai; Lucia Specia; | arxiv-cs.CL | 2019-07-01 |
| 408 | Eliciting Knowledge From Experts:Automatic Transcript Parsing For Cognitive Task Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a weakly-supervised information extraction framework for automated CTA transcript parsing. |
Junyi Du; He Jiang; Jiaming Shen; Xiang Ren; | arxiv-cs.CL | 2019-06-26 |
| 409 | Exploiting Entity BIO Tag Embeddings And Multi-task Learning For Relation Extraction With Imbalanced Data IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To mitigate this problem, we propose a multi-task architecture which jointly trains a model to perform relation identification with cross-entropy loss and relation classification with ranking loss. |
WEI YE et. al. | arxiv-cs.CL | 2019-06-20 |
| 410 | Fine-tuning Pre-Trained Transformer Language Models To Distantly Supervised Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this gap, we utilize a pre-trained language model, the OpenAI Generative Pre-trained Transformer (GPT) [Radford et al., 2018]. |
Christoph Alt; Marc Hübner; Leonhard Hennig; | arxiv-cs.CL | 2019-06-19 |
| 411 | REflex: Flexible Framework For Relation Extraction In Multiple Domains IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we build a unifying framework for RE, applying this on three highly used datasets (from the general, biomedical and clinical domains) with the ability to be extendable to new datasets. |
Geeticka Chauhan; Matthew B. A. McDermott; Peter Szolovits; | arxiv-cs.CL | 2019-06-19 |
| 412 | Attention Guided Graph Convolutional Networks For Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose Attention Guided Graph Convolutional Networks (AGGCNs), a novel model which directly takes full dependency trees as inputs. |
Zhijiang Guo; Yan Zhang; Wei Lu; | arxiv-cs.CL | 2019-06-18 |
| 413 | Transfer Learning For Causal Sentence Detection IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We consider the task of detecting sentences that express causality, as a step towards mining causal relations from texts. |
Manolis Kyriakakis; Ion Androutsopoulos; Joan Ginés i Ametllé; Artur Saudabayev; | arxiv-cs.CL | 2019-06-18 |
| 414 | BERE: An Accurate Distantly Supervised Biomedical Entity Relation Extraction Network IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose BERE, a deep learning based model which uses Gumbel Tree-GRU to learn sentence structures and joint embedding to incorporate entity information. Because the existing dataset are relatively small, we further construct a much larger drug-target interaction extraction (DTIE) dataset by distant supervision. |
Lixiang Hong; JinJian Lin; Jiang Tao; Jianyang Zeng; | arxiv-cs.CL | 2019-06-17 |
| 415 | Multi-Level Matching And Aggregation Network For Few-Shot Relation Classification IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a multi-level matching and aggregation network (MLMAN) for few-shot relation classification. |
Zhi-Xiu Ye; Zhen-Hua Ling; | arxiv-cs.CL | 2019-06-16 |
| 416 | Spatial-Aware Graph Relation Network For Large-Scale Object Detection IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we introduce a Spatial-aware Graph Relation Network (SGRN) to adaptive discover and incorporate key semantic and spatial relationships for reasoning over each object. |
Hang Xu; Chenhan Jiang; Xiaodan Liang; Zhenguo Li; | cvpr | 2019-06-14 |
| 417 | DocRED: A Large-Scale Document-Level Relation Extraction Dataset IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In order to verify the challenges of document-level RE, we implement recent state-of-the-art methods for RE and conduct a thorough evaluation of these methods on DocRED. |
YUAN YAO et. al. | arxiv-cs.CL | 2019-06-14 |
| 418 | On Exploring Undetermined Relationships For Visual Relationship Detection IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we explore the beneficial effect of undetermined relationships on visual relationship detection. |
Yibing Zhan; Jun Yu; Ting Yu; Dacheng Tao; | cvpr | 2019-06-14 |
| 419 | Antonym-Synonym Classification Based On New Sub-space Embeddings IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a novel approach entirely based on pre-trained embeddings. |
Muhammad Asif Ali; Yifang Sun; Xiaoling Zhou; Wei Wang; Xiang Zhao; | arxiv-cs.CL | 2019-06-13 |
| 420 | A Structured Learning Approach To Temporal Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper suggests that it is important to take these dependencies into account while learning to identify these relations and proposes a structured learning approach to address this challenge. |
Qiang Ning; Zhili Feng; Dan Roth; | arxiv-cs.CL | 2019-06-12 |
| 421 | Inter-sentence Relation Extraction With Document-level Graph Convolutional Neural Network IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present a novel inter-sentence relation extraction model that builds a labelled edge graph convolutional neural network model on a document-level graph. |
Sunil Kumar Sahu; Fenia Christopoulou; Makoto Miwa; Sophia Ananiadou; | arxiv-cs.CL | 2019-06-11 |
| 422 | Matching The Blanks: Distributional Similarity For Relation Learning IF:4 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we build on extensions of Harris’ distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. |
Livio Baldini Soares; Nicholas FitzGerald; Jeffrey Ling; Tom Kwiatkowski; | arxiv-cs.CL | 2019-06-07 |
| 423 | Improving Relation Extraction By Pre-trained Language Representations IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address these limitations, we introduce TRE, a Transformer for Relation Extraction, extending the OpenAI Generative Pre-trained Transformer [Radford et al., 2018]. |
Christoph Alt; Marc Hübner; Leonhard Hennig; | arxiv-cs.CL | 2019-06-07 |
| 424 | Long-tail Relation Extraction Via Knowledge Graph Embeddings And Graph Convolution Networks IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We propose a distance supervised relation extraction approach for long-tailed, imbalanced data which is prevalent in real-world settings. |
NINGYU ZHANG et. al. | naacl | 2019-06-02 |
| 425 | Connecting Language And Knowledge With Heterogeneous Representations For Neural Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We help close the gap with a framework that unifies the learning of RE and KBE models leading to significant improvements over the state-of-the-art in RE. |
Peng Xu; Denilson Barbosa,; | naacl | 2019-06-02 |
| 426 | Distant Supervision Relation Extraction With Intra-Bag And Inter-Bag Attentions IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a neural relation extraction method to deal with the noisy training data generated by distant supervision. |
Zhi-Xiu Ye; Zhen-Hua Ling,; | naacl | 2019-06-02 |
| 427 | Relation Extraction Using Explicit Context Conditioning IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We refer to such indirect relations as second-order relations, and describe an efficient implementation for computing them. |
Gaurav Singh; Parminder Bhatia,; | naacl | 2019-06-02 |
| 428 | Sentence Embedding Alignment For Lifelong Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Specifically, we utilize an explicit alignment model to mitigate the sentence embedding distortion of learned model when training on new data and new relations. |
HONG WANG et. al. | naacl | 2019-06-02 |
| 429 | OpenCeres: When Open Information Extraction Meets The Semi-Structured Web IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we define the problem of OpenIE from semi-structured websites to extract such facts, and present an approach for solving it. We also introduce a labeled evaluation dataset to motivate research in this area. |
Colin Lockard; Prashant Shiralkar; Xin Luna Dong,; | naacl | 2019-06-02 |
| 430 | Document-Level N-ary Relation Extraction With Multiscale Representation Learning IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel multiscale neural architecture for document-level n-ary relation extraction. |
Robin Jia; Cliff Wong; Hoifung Poon,; | naacl | 2019-06-02 |
| 431 | Combining Distant And Direct Supervision For Neural Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We improve such models by combining the distant supervision data with an additional directly-supervised data, which we use as supervision for the attention weights. |
Iz Beltagy; Kyle Lo; Waleed Ammar,; | naacl | 2019-06-02 |
| 432 | A Silver Standard Corpus Of Human Phenotype-Gene Relations IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the Phenotype-Gene Relations (PGR) corpus, a silver standard corpus of human phenotype and gene annotations and their relations. We generated this corpus using Named-Entity Recognition tools, whose results were partially evaluated by eight curators, obtaining a precision of 87.01%. |
Diana Sousa; Andre Lamurias; Francisco M Couto,; | naacl | 2019-06-02 |
| 433 | Frowning Frodo, Wincing Leia, And A Seriously Great Friendship: Learning To Classify Emotional Relationships Of Fictional Characters IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we combine these aspects into a unified framework to classify emotional relationships of fictional characters. |
Evgeny Kim; Roman Klinger,; | naacl | 2019-06-02 |
| 434 | Structured Minimally Supervised Learning For Neural Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an approach to minimally supervised relation extraction that combines the benefits of learned representations and structured learning, and accurately predicts sentence-level relation mentions given only proposition-level supervision from a KB. |
Fan Bai; Alan Ritter,; | naacl | 2019-06-02 |
| 435 | UHop: An Unrestricted-Hop Relation Extraction Framework For Knowledge-Based Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose UHop, an unrestricted-hop framework which relaxes this restriction by use of a transition-based search framework to replace the relation-chain-based search one. |
Zi-Yuan Chen; Chih-Hung Chang; Yi-Pei Chen; Jijnasa Nayak; Lun-Wei Ku,; | naacl | 2019-06-02 |
| 436 | Exploiting Noisy Data In Distant Supervision Relation Classification IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Different from previous works that underutilize noisy data which inherently characterize the property of classification, in this paper, we propose RCEND, a novel framework to enhance Relation Classification by Exploiting Noisy Data. |
Kaijia Yang; Liang He; Xin-Yu Dai; Shujian Huang; Jiajun Chen,; | naacl | 2019-06-02 |
| 437 | A Richer-but-Smarter Shortest Dependency Path With Attentive Augmentation For Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a novel model that combines the advantages of these two approaches. |
Duy-Cat Can; Hoang-Quynh Le; Quang-Thuy Ha; Nigel Collier,; | naacl | 2019-06-02 |
| 438 | Improving Knowledge Base Construction From Robust Infobox Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a robust approach that tackles all three challenges. |
Boya Peng; Yejin Huh; Xiao Ling; Michele Banko,; | naacl | 2019-06-02 |
| 439 | Learning Relational Representations By Analogy Using Hierarchical Siamese Networks IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We address relation extraction as an analogy problem by proposing a novel approach to learn representations of relations expressed by their textual mentions. Following this idea, we collect a large set of analogous pairs by matching triples in knowledge bases with web-scale corpora through distant supervision. |
Gaetano Rossiello; Alfio Gliozzo; Robert Farrell; Nicolas Fauceglia; Michael Glass,; | naacl | 2019-06-02 |
| 440 | GAN Driven Semi-distant Supervision For Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this issue, we propose a novel semi-distant supervision approach for relation extraction by constructing a small accurate dataset and properly leveraging numerous instances without relation labels. |
Pengshuai Li; Xinsong Zhang; Weijia Jia; Hai Zhao,; | naacl | 2019-06-02 |
| 441 | Relation Extraction With Temporal Reasoning Based On Memory Augmented Distant Supervision IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper formulates the problem of relation extraction with temporal reasoning and proposes a solution to predict whether two given entities participate in a relation at a given time spot. For this purpose, we construct a dataset called WIKI-TIME which additionally includes the valid period of a certain relation of two entities in the knowledge base. |
Jianhao Yan; Lin He; Ruqin Huang; Jian Li; Ying Liu,; | naacl | 2019-06-02 |
| 442 | Relation Classification Using Segment-Level Attention-based CNN And Dependency-based RNN IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new model effectively combining Segment-level Attention-based Convolutional Neural Networks (SACNNs) and Dependency-based Recurrent Neural Networks (DepRNNs). |
Van-Hien Tran; Van-Thuy Phi; Hiroyuki Shindo; Yuji Matsumoto,; | naacl | 2019-06-02 |
| 443 | Using Neural Networks For Relation Extraction From Biomedical Literature IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Several relation extraction approaches have been proposed to identify relations between concepts in biomedical literature, namely, using neural networks algorithms. |
Diana Sousa; Andre Lamurias; Francisco M. Couto; | arxiv-cs.CL | 2019-05-27 |
| 444 | Learning Dependency Structures For Weak Supervision Models IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We focus on a robust PCA-based algorithm for learning these dependency structures, establish improved theoretical recovery rates, and outperform existing methods on various real-world tasks. |
Paroma Varma; Frederic Sala; Ann He; Alexander Ratner; Christopher Re; | icml | 2019-05-24 |
| 445 | A Multi-Task Learning Framework For Extracting Drugs And Their Interactions From Drug Labels IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Herein, we describe our approach to tackling tasks one and two of the DDI track, which corresponds to named entity recognition (NER) and sentence-level relation extraction respectively. |
Tung Tran; Ramakanth Kavuluru; Halil Kilicoglu; | arxiv-cs.CL | 2019-05-17 |
| 446 | Neural Metric Learning For Fast End-to-End Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We introduce a novel neural architecture utilizing the table structure, based on repeated applications of 2D convolutions for pooling local dependency and metric-based features, that improves on the state-of-the-art without the need for global optimization. |
Tung Tran; Ramakanth Kavuluru; | arxiv-cs.CL | 2019-05-17 |
| 447 | Entity-Relation Extraction As Multi-Turn Question Answering IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a new paradigm for the task of entity-relation extraction. |
XIAOYA LI et. al. | arxiv-cs.CL | 2019-05-14 |
| 448 | Assessing The Difficulty Of Classifying ConceptNet Relations In A Multi-Label Classification Setting IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We explore a neural open world multi-label classification approach that focuses on the evaluation of classification accuracy for individual relations. |
Maria Becker; Michael Staniek; Vivi Nastase; Anette Frank; | arxiv-cs.CL | 2019-05-14 |
| 449 | Learning Dual Retrieval Module For Semi-supervised Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we leverage a key insight that retrieving sentences expressing a relation is a dual task of predicting the relation label for a given sentence-two tasks are complementary to each other and can be optimized jointly for mutual enhancement. |
Hongtao Lin; Jun Yan; Meng Qu; Xiang Ren; | www | 2019-05-13 |
| 450 | MCVAE: Margin-based Conditional Variational Autoencoder For Relation Classification And Pattern Generation IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: To address this challenge, in this paper, we propose to employ a generative model, called conditional variational autoencoder (CVAE), to handle the pattern sparsity. |
FENGLONG MA et. al. | www | 2019-05-13 |
| 451 | RelExt: Relation Extraction Using Deep Learning Approaches For Cybersecurity Knowledge Graph Improvement IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we propose a system to create semantic triples over cybersecurity text, using deep learning approaches to extract possible relationships. |
ADITYA PINGLE et. al. | arxiv-cs.CL | 2019-05-07 |
| 452 | A Relation Extraction Approach For Clinical Decision Support IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we investigate how semantic relations between concepts extracted from medical documents can be employed to improve the retrieval of medical literature. |
Maristella Agosti; Giorgio Maria Di Nunzio; Stefano Marchesin; Gianmaria Silvello; | arxiv-cs.IR | 2019-05-03 |
| 453 | Improving Visual Relation Detection Using Depth Maps IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we study the effect of using different object features with a focus on depth maps. To enable this study, we release a new synthetic dataset of depth maps, VG-Depth, as an extension to Visual Genome (VG). |
Sahand Sharifzadeh; Sina Moayed Baharlou; Max Berrendorf; Rajat Koner; Volker Tresp; | arxiv-cs.CV | 2019-05-02 |
| 454 | Logician: A Unified End-to-End Neural Approach For Open-Domain Information Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we consider the problem of open information extraction (OIE) for extracting entity and relation level intermediate structures from sentences in open-domain. We publicly release a data set which contains more than forty thousand sentences and the corresponding facts in the SAOKE format labeled by crowd-sourcing. |
MINGMING SUN et. al. | arxiv-cs.CL | 2019-04-29 |
| 455 | Contextualized Word Embeddings Enhanced Event Temporal Relation Extraction For Story Understanding IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this work, we establish strong baselines for event temporal relation extraction on two under-explored story narrative datasets: Richer Event Description (RED) and Causal and Temporal Relation Scheme (CaTeRS). |
Rujun Han; Mengyue Liang; Bashar Alhafni; Nanyun Peng; | arxiv-cs.CL | 2019-04-26 |
| 456 | A Bag-of-concepts Model Improves Relation Extraction In A Narrow Knowledge Domain With Limited Data IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper focuses on a traditional relation extraction task in the context of limited annotated data and a narrow knowledge domain. |
Jiyu Chen; Karin Verspoor; Zenan Zhai; | arxiv-cs.LG | 2019-04-24 |
| 457 | Simple BERT Models For Relation Extraction And Semantic Role Labeling IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present simple BERT-based models for relation extraction and semantic role labeling. |
Peng Shi; Jimmy Lin; | arxiv-cs.CL | 2019-04-10 |
| 458 | Advancing NLP With Cognitive Language Processing Signals IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an extensive investigation of the benefits and limitations of using cognitive processing data for NLP. |
NORA HOLLENSTEIN et. al. | arxiv-cs.CL | 2019-04-04 |
| 459 | Document-Level $N$-ary Relation Extraction With Multiscale Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose a novel multiscale neural architecture for document-level $n$-ary relation extraction. |
Robin Jia; Cliff Wong; Hoifung Poon; | arxiv-cs.CL | 2019-04-04 |
| 460 | UHop: An Unrestricted-Hop Relation Extraction Framework For Knowledge-Based Question Answering IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we propose UHop, an unrestricted-hop framework which relaxes this restriction by use of a transition-based search framework to replace the relation-chain-based search one. |
Zi-Yuan Chen; Chih-Hung Chang; Yi-Pei Chen; Jijnasa Nayak; Lun-Wei Ku; | arxiv-cs.CL | 2019-04-02 |
| 461 | Distant Supervision Relation Extraction With Intra-Bag And Inter-Bag Attentions IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents a neural relation extraction method to deal with the noisy training data generated by distant supervision. |
Zhi-Xiu Ye; Zhen-Hua Ling; | arxiv-cs.CL | 2019-03-29 |
| 462 | Frowning Frodo, Wincing Leia, And A Seriously Great Friendship: Learning To Classify Emotional Relationships Of Fictional Characters IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we combine these aspects into a unified framework to classify emotional relationships of fictional characters. |
Evgeny Kim; Roman Klinger; | arxiv-cs.CL | 2019-03-29 |
| 463 | Structured Minimally Supervised Learning For Neural Relation Extraction IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: We present an approach to minimally supervised relation extraction that combines the benefits of learned representations and structured learning, and accurately predicts sentence-level relation mentions given only proposition-level supervision from a KB. |
Fan Bai; Alan Ritter; | arxiv-cs.CL | 2019-03-29 |
| 464 | A General FOFE-net Framework For Simple And Effective Question Answering Over Knowledge Bases IF:2 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: Inspired by a previous work that builds a strong KB-QA baseline, we propose a simple but general neural model composed of fixed-size ordinally forgetting encoding (FOFE) and deep neural networks, called FOFE-net to solve KB-QA problem at different stages. |
Dekun Wu; Nana Nosirova; Hui Jiang; Mingbin Xu; | arxiv-cs.CL | 2019-03-29 |
| 465 | A Silver Standard Corpus Of Human Phenotype-Gene Relations IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: This paper presents the Phenotype-Gene Relations (PGR) corpus, a silver standard corpus of human phenotype and gene annotations and their relations. We generated this corpus using Named-Entity Recognition tools, whose results were partially evaluated by eight curators, obtaining a precision of 87.01%. |
Diana Sousa; Andre Lamurias; Francisco M. Couto; | arxiv-cs.CL | 2019-03-26 |
| 466 | Connecting Language And Knowledge With Heterogeneous Representations For Neural Relation Extraction IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Abstract: Knowledge Bases (KBs) require constant up-dating to reflect changes to the world they represent. For general purpose KBs, this is often done through Relation Extraction (RE), the … |
Peng Xu; Denilson Barbosa; | arxiv-cs.CL | 2019-03-25 |
| 467 | Relation Extraction Between The Clinical Entities Based On The Shortest Dependency Path Based LSTM IF:3 Related Papers Related Patents Related Grants Related Orgs Related Experts Details Highlight: In this paper, we present an efficient relation extraction system based on the shortest dependency path (SDP) generated from the dependency parsed tree of the sentence. |