Paper Digest: Recent Papers on Question Answering
Paper Digest Team extracted all recent Question Answering 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 Question Answering
| Title | Author(s) | Highlight | Category | Date | |
|---|---|---|---|---|---|
| 1 | Neural Passage Retrieval With Improved Negative Contrast | JING LU et. al. | In this paper we explore the effects of negative sampling in dual encoder models used to retrieve passages for automatic question answering. | CS.arxiv | 2020-10-23 |
| 2 | Retrieve, Rerank, Read, Then Iterate: Answering Open-Domain Questions Of Arbitrary Complexity From Text | PENG QI et. al. | To address these limitations, we propose a unified system to answer open-domain questions of arbitrary complexity directly from text that works with off-the-shelf retrieval systems on arbitrary text collections. To emulate a more realistic setting, we also constructed a new unified benchmark by collecting about 200 multi-hop questions that require three Wikipedia pages to answer, and combining them with existing datasets. | CS.arxiv | 2020-10-23 |
| 3 | EIGEN: Event Influence GENeration Using Pre-trained Language Models | AMAN MADAAN et. al. | In this paper, we present EIGEN – a method to leverage pre-trained language models to generate event influences conditioned on a context, nature of their influence, and the distance in a reasoning chain. | CS.arxiv | 2020-10-22 |
| 4 | Multilingual Synthetic Question And Answer Generation For Cross-Lingual Reading Comprehension | SIAMAK SHAKERI et. al. | We propose a simple method to generate large amounts of multilingual question and answer pairs by a single generative model. | CS.arxiv | 2020-10-22 |
| 5 | Summarizing Utterances From Japanese Assembly Minutes Using Political Sentence-BERT-based Method For QA Lab-PoliInfo-2 Task Of NTCIR-15 | DAIKI SHIRAFUJI et. al. | This paper describes our approach to solving the task and discusses its results. | CS.arxiv | 2020-10-22 |
| 6 | XOR QA: Cross-lingual Open-Retrieval Question Answering | AKARI ASAI et. al. | Based on this dataset, we introduce three new tasks that involve cross-lingual document retrieval using multi-lingual and English resources. We construct a large-scale dataset built on questions from TyDi QA lacking same-language answers. | CS.arxiv | 2020-10-22 |
| 7 | Challenges In Information Seeking QA:Unanswerable Questions And Paragraph Retrieval | AKARI ASAI et. al. | We analyze two such datasets (Natural Questions and TyDi QA) to identify remaining headrooms: paragraph selection and answerability classification, i.e. determining whether the paired evidence document contains the answer to the query or not. | CS.arxiv | 2020-10-22 |
| 8 | Is Retriever Merely An Approximator Of Reader? | SOHEE YANG et. al. | Experimental results show that our method can enhance the document recall rate as well as the end-to-end QA accuracy of off-the-shelf retrievers in open-domain QA tasks. | CS.arxiv | 2020-10-21 |
| 9 | Exploring Sequence-to-Sequence Models For SPARQL Pattern Composition | ANAND PANCHBHAI et. al. | In this short paper, we explore the use of architectures based on Neural Machine Translation called Neural SPARQL Machines to learn pattern compositions. | CS.arxiv | 2020-10-21 |
| 10 | Kwame: A Bilingual AI Teaching Assistant For Online SuaCode Courses | GEORGE BOATENG | Given the multilingual context of our students (learners across 38 African countries), in this work, we developed an AI Teaching Assistant (Kwame) that provides answers to students’ coding questions from our SuaCode courses in English and French. | CS.arxiv | 2020-10-21 |
| 11 | RECONSIDER: Re-Ranking Using Span-Focused Cross-Attention For Open Domain Question Answering | SRINIVASAN IYER et. al. | We develop a simple and effective re-ranking approach (RECONSIDER) for span-extraction tasks, that improves upon the performance of large pre-trained MRC models. | CS.arxiv | 2020-10-21 |
| 12 | Removing Bias In Multi-modal Classifiers: Regularization By Maximizing Functional Entropies | ITAI GAT et. al. | To alleviate this shortcoming, we propose a novel regularization term based on the functional entropy. | CS.arxiv | 2020-10-21 |
| 13 | Unsupervised Deep Learning Based Multiple Choices Question Answering: Start Learning From Basic Knowledge | CHI-LIANG LIU et. al. | In this paper, we study the possibility of almost unsupervised Multiple Choices Question Answering (MCQA). | CS.arxiv | 2020-10-21 |
| 14 | Knowledge Distillation For Improved Accuracy In Spoken Question Answering | CHENYU YOU et. al. | To address the issue, we present a novel distillation framework. | CS.arxiv | 2020-10-21 |
| 15 | Contextualized Attention-based Knowledge Transfer For Spoken Conversational Question Answering | CHENYU YOU et. al. | To overcome the problem, we propose CADNet, a novel contextualized attention-based distillation approach, which applies both cross-attention and self-attention to obtain ASR-robust contextualized embedding representations of the passage and dialogue history for performance improvements. | CS.arxiv | 2020-10-21 |
| 16 | Open Question Answering Over Tables And Text | WENHU CHEN et. al. | Most questions in OTT-QA require multi-hop inference across tabular data and unstructured text, and the evidence required to answer a question can be distributed in different ways over these two types of input, making evidence retrieval challenging—our baseline model using an iterative retriever and BERT-based reader achieves an exact match score less than 10%. | CS.arxiv | 2020-10-20 |
| 17 | Pushing The Limits Of AMR Parsing With Self-Learning | YOUNG-SUK LEE et. al. | In this paper, we explore different ways in which trained models can be applied to improve AMR parsing performance, including generation of synthetic text and AMR annotations as well as refinement of actions oracle. | CS.arxiv | 2020-10-20 |
| 18 | Bi-directional Cognitive Thinking Network For Machine Reading Comprehension | WEI PENG et. al. | We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory. | CS.arxiv | 2020-10-20 |
| 20 | BiST: Bi-directional Spatio-Temporal Reasoning For Video-Grounded Dialogues | HUNG LE et. al. | To address this drawback, we propose Bi-directional Spatio-Temporal Learning (BiST), a vision-language neural framework for high-resolution queries in videos based on textual cues. | CS.arxiv | 2020-10-20 |
| 21 | Extracting Procedural Knowledge From Technical Documents | SHIVALI AGARWAL et. al. | In this work, we cover some of this ground by — 1) Providing insights on how structural and linguistic properties of documents can be grouped to define types of procedures, 2) Analyzing documents to extract the relevant linguistic and structural properties, and 3) Formulating procedure identification as a classification problem that leverages the features of the document derived from the above analysis. | CS.arxiv | 2020-10-20 |
| 22 | Event-QA: A Dataset For Event-Centric Question Answering Over Knowledge Graphs | TARCÍSIO SOUZA COSTA et. al. | In this paper, we present the Event-QA dataset for answering event-centric questions over knowledge graphs. | CS.cikm | 2020-10-19 |
| 23 | Question Generation For Supporting Informational Query Intents | XUSEN YIN et. al. | In this work, we aim to generate self-explanatory questions that focus on the main document topics and are answerable with variable length passages as appropriate. | CS.arxiv | 2020-10-19 |
| 25 | Learning To Generate Reformulation Actions For Scalable Conversational Query Understanding | ZIHAN XU et. al. | For action generation, we propose a multi-task learning framework enhanced by coreference resolution, and introduce grammar constraints into the decoding process. | CS.cikm | 2020-10-19 |
| 26 | Hierarchical Query Graph Generation For Complex Question Answering Over Knowledge Graph | YUNQI QIU et. al. | This paper proposes a Director-Actor-Critic framework to overcome these challenges. | CS.cikm | 2020-10-19 |
| 27 | Do People And Neural Nets Pay Attention To The Same Words: Studying Eye-tracking Data For Non-factoid QA Evaluation | VALERIA BOLOTOVA et. al. | Similarity was found, consequently, we propose a method to exploit the BERT attention map to generate suggestions that simulate eye gaze during user evaluation. | CS.cikm | 2020-10-19 |
| 28 | Fine-Grained Relevance Annotations For Multi-Task Document Ranking And Question Answering | SEBASTIAN HOFSTÄTTER et. al. | In this work, we present FiRA: a novel dataset of Fine-Grained Relevance Annotations. | CS.cikm | 2020-10-19 |
| 29 | Neural Relation Extraction On Wikipedia Tables For Augmenting Knowledge Graphs | ERIN MACDONALD et. al. | 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. | CS.cikm | 2020-10-19 |
| 30 | AliMeKG: Domain Knowledge Graph Construction And Application In E-commerce | FENG-LIN LI et. al. | In the paper, we systematically introduce how we construct domain knowledge graph from free text, and demonstrate its business value with several applications. | CS.cikm | 2020-10-19 |
| 31 | Technical Question Answering Across Tasks And Domains | WENHAO YU et. al. | In this paper, we propose a novel framework of deep transfer learning to effectively address technical QA across tasks and domains. | CS.arxiv | 2020-10-19 |
| 32 | Continual Domain Adaptation For Machine Reading Comprehension | LIXIN SU et. al. | To tackle the CDA task, we propose several BERT-based continual learning MRC models using either regularization-based methodology or dynamic-architecture paradigm. | CS.cikm | 2020-10-19 |
| 33 | Offline Evaluation By Maximum Similarity To An Ideal Ranking | CHARLES L. A. CLARKE et. al. | Rather than propose extensions to these measures, we instead propose a radical simplification to replace them. | CS.cikm | 2020-10-19 |
| 34 | CauseNet: Towards A Causality Graph Extracted From The Web | STEFAN HEINDORF et. al. | Notwithstanding this challenge, we compile CauseNet, a large-scale knowledge base of claimed causal relations between causal concepts. | CS.cikm | 2020-10-19 |
| 35 | Schema2QA: High-Quality And Low-Cost Q&A Agents For The Structured Web | SILEI XU et. al. | This paper proposes Schema2QA, an open-source toolkit that can generate a Q&A system from a database schema augmented with a few annotations for each field. | CS.cikm | 2020-10-19 |
| 36 | Opinion-aware Answer Generation For Review-driven Question Answering In E-Commerce | YANG DENG et. al. | In this paper, we tackle opinion-aware answer generation by jointly learning answer generation and opinion mining tasks with a unified model. | CS.cikm | 2020-10-19 |
| 37 | Knowledge Graph-based Question Answering With Electronic Health Records | JUNWOO PARK et. al. | We hypothesize that the graph-based approach is more suitable for EHR QA as graphs can represent relations between entities and values more naturally compared to tables, which essentially require JOIN operations. | CS.arxiv | 2020-10-19 |
| 38 | The RELX Dataset And Matching The Multilingual Blanks For Cross-Lingual Relation Classification | ABDULLATIF KÖKSAL et. al. | 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. | CS.arxiv | 2020-10-19 |
| 39 | Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder For Long-Form Document Matching | LIU YANG et. al. | In this paper, we address the issue by proposing the Siamese Multi-depth Transformer-based Hierarchical (SMITH) Encoder for long-form document matching. | CS.cikm | 2020-10-19 |
| 40 | Feature Extraction For Large-Scale Text Collections | LUKE GALLAGHER et. al. | In this paper, we introduce Fxt, an open-source framework to perform efficient and scalable feature extraction. | CS.cikm | 2020-10-19 |
| 41 | BERTnesia: Investigating The Capture And Forgetting Of Knowledge In BERT | JONAS WALLAT et. al. | In this paper, we probe BERT specifically to understand and measure the relational knowledge it captures. | CS.arxiv | 2020-10-19 |
| 42 | Understanding Unnatural Questions Improves Reasoning Over Text | XIAO-YU GUO et. al. | In this paper, we address the challenge of learning a high-quality programmer (parser) by projecting natural human-generated questions into unnatural machine-generated questions which are more convenient to parse. | CS.arxiv | 2020-10-19 |
| 43 | Better Distractions: Transformer-based Distractor Generation And Multiple Choice Question Filtering | JEROEN OFFERIJNS et. al. | In this work, we train a GPT-2 language model to generate three distractors for a given question and text context, using the RACE dataset. | CS.arxiv | 2020-10-19 |
| 44 | Knowledge-guided Open Attribute Value Extraction With Reinforcement Learning | YE LIU et. al. | In this work, we propose a knowledge-guided reinforcement learning (RL) framework for open attribute value extraction. | CS.arxiv | 2020-10-18 |
| 45 | Towards Interpreting BERT For Reading Comprehension Based QA | SAHANA RAMNATH et. al. | In this work, we attempt to interpret BERT for RCQA. | CS.arxiv | 2020-10-18 |
| 46 | Towards Data Distillation For End-to-end Spoken Conversational Question Answering | CHENYU YOU et. al. | To this end, instead of adopting automatically generated speech transcripts with highly noisy data, we propose a novel unified data distillation approach, DDNet, which directly fuse audio-text features to reduce the misalignment between automatic speech recognition hypotheses and the reference transcriptions. | CS.arxiv | 2020-10-18 |
| 47 | Question Answering Over Knowledge Base Using Language Model Embeddings | SAI SHARATH JAPA et. al. | In this paper, we focused on using a pre-trained language model for the Knowledge Base Question Answering task. | CS.arxiv | 2020-10-17 |
| 48 | RocketQA: An Optimized Training Approach To Dense Passage Retrieval For Open-Domain Question Answering | YINGQI QU YUCHEN DING et. al. | To address these challenges, we propose an optimized training approach, called RocketQA, to improving dense passage retrieval. | CS.arxiv | 2020-10-16 |
| 49 | New Ideas And Trends In Deep Multimodal Content Understanding: A Review | WEI CHEN et. al. | Unlike classic reviews of deep learning where monomodal image classifiers such as VGG, ResNet and Inception module are central topics, this paper will examine recent multimodal deep models and structures, including auto-encoders, generative adversarial nets and their variants. | CS.arxiv | 2020-10-16 |
| 50 | Delaying Interaction Layers In Transformer-based Encoders For Efficient Open Domain Question Answering | WISSAM SIBLINI et. al. | In this paper, we propose a more direct and complementary solution which consists in applying a generic change in the architecture of transformer-based models to delay the attention between subparts of the input and allow a more efficient management of computations. | CS.arxiv | 2020-10-16 |
| 51 | Answer-checking In Context: A Multi-modal FullyAttention Network For Visual Question Answering | HANTAO HUANG et. al. | In this paper, we mimic this process and propose a fully attention based VQA architecture. | CS.arxiv | 2020-10-16 |
| 52 | QA2Explanation: Generating And Evaluating Explanations For Question Answering Systems Over Knowledge Graph | SAEEDEH SHEKARPOUR et. al. | To address this challenge, in this paper, we develop an automatic approach for generating explanations during various stages of a pipeline-based QA system. | CS.arxiv | 2020-10-16 |
| 53 | Natural Language Rationales With Full-Stack Visual Reasoning: From Pixels To Semantic Frames To Commonsense Graphs | ANA MARASOVIĆ et. al. | We present Rationale^VT Transformer, an integrated model that learns to generate free-text rationales by combining pretrained language models with object recognition, grounded visual semantic frames, and visual commonsense graphs. | CS.arxiv | 2020-10-15 |
| 54 | Hierarchical Poset Decoding For Compositional Generalization In Language | YINUO GUO et. al. | In this paper, we propose a novel hierarchical poset decoding paradigm for compositional generalization in language. | CS.arxiv | 2020-10-15 |
| 55 | Length-Adaptive Transformer: Train Once With Length Drop, Use Anytime With Search | GYUWAN KIM et. al. | In this paper, we extend PoWER-BERT to address this issue of inefficiency and redundancy. | CS.arxiv | 2020-10-14 |
| 56 | A Graph Representation Of Semi-structured Data For Web Question Answering | XINGYAO ZHANG et. al. | In this paper, we propose a novel graph representation of Web tables and lists based on a systematic categorization of the components in semi-structured data as well as their relations. | CS.arxiv | 2020-10-14 |
| 57 | CoRel: Seed-Guided Topical Taxonomy Construction By Concept Learning And Relation Transferring | JIAXIN HUANG et. al. | In this paper, we propose a method for seed-guided topical taxonomy construction, which takes a corpus and a seed taxonomy described by concept names as input, and constructs a more complete taxonomy based on user’s interest, wherein each node is represented by a cluster of coherent terms. | CS.arxiv | 2020-10-13 |
| 58 | Does My Multimodal Model Learn Cross-modal Interactions? It’s Harder To Tell Than You Might Think! | JACK HESSEL et. al. | We propose a new diagnostic tool, empirical multimodally-additive function projection (EMAP), for isolating whether or not cross-modal interactions improve performance for a given model on a given task. | CS.arxiv | 2020-10-13 |
| 59 | Finding Minimum Connected Subgraphs With Ontology Exploration On Large RDF Data | XIANGNAN REN et. al. | In this paper, we study the following problem: given a knowledge graph (KG) and a set of input vertices (representing concepts or entities) and edge labels, we aim to find the smallest connected subgraphs containing all of the inputs. | CS.arxiv | 2020-10-13 |
| 60 | F1 Is Not Enough! Models And Evaluation Towards User-Centered Explainable Question Answering | HENDRIK SCHUFF et. al. | As a remedy, we propose a hierarchical model and a new regularization term to strengthen the answer-explanation coupling as well as two evaluation scores to quantify the coupling. | CS.arxiv | 2020-10-13 |
| 61 | Photo Stream Question Answer | WENQIAO ZHANG et. al. | In this paper, we present a new visual question answering (VQA) task — Photo Stream QA, which aims to answer the open-ended questions about a narrative photo stream. | CS.mm | 2020-10-12 |
| 62 | End-to-End Synthetic Data Generation For Domain Adaptation Of Question Answering Systems | SIAMAK SHAKERI et. al. | We propose an end-to-end approach for synthetic QA data generation. | CS.arxiv | 2020-10-12 |
| 63 | Multi-modal Multi-relational Feature Aggregation Network For Medical Knowledge Representation Learning | YINGYING ZHANG et. al. | In this paper, we propose a Multi-modal Multi-Relational Feature Aggregation Network (MMRFAN) for medical knowledge representation learning. | CS.mm | 2020-10-12 |
| 64 | Counterfactual Variable Control For Robust And Interpretable Question Answering | SICHENG YU et. al. | In this paper, we inspect such spurious capability of QA models using causal inference. | CS.arxiv | 2020-10-12 |
| 65 | DeVLBert: Learning Deconfounded Visio-Linguistic Representations | SHENGYU ZHANG et. al. | In this paper, we propose to investigate the problem of out-of-domain visio-linguistic pretraining, where the pretraining data distribution differs from that of downstream data on which the pretrained model will be fine-tuned. | CS.mm | 2020-10-12 |
| 66 | Multi-modal Attentive Graph Pooling Model For Community Question Answer Matching | JUN HU et. al. | In this paper, we propose a multi-modal attentive graph pooling approach (MMAGP) to model the multi-modal content of questions and answers with GNNs in a unified framework, which explores the multi-modal and redundant properties of CQA systems. | CS.mm | 2020-10-12 |
| 67 | Medical Visual Question Answering Via Conditional Reasoning | LI-MING ZHAN et. al. | In this paper, we propose a novel conditional reasoning framework for Med-VQA, aiming to automatically learn effective reasoning skills for various Med-VQA tasks. | CS.mm | 2020-10-12 |
| 68 | Neural-Symbolic Reasoning On Knowledge Graphs | JING ZHANG et. al. | In this survey, we take a thorough look at the development of the symbolic reasoning, neural reasoning and the neural-symbolic reasoning on knowledge graphs. | CS.arxiv | 2020-10-12 |
| 69 | Cascade Reasoning Network For Text-based Visual Question Answering | FEN LIU et. al. | We study the problem of text-based visual question answering (T-VQA) in this paper. | CS.mm | 2020-10-12 |
| 70 | Learning Self-Supervised Multimodal Representations Of Human Behaviour | ABHINAV SHUKLA | In this extended abstract, I present the direction of research that I have followed during the first half of my PhD, along with ideas and work in progress for the second half. | CS.mm | 2020-10-12 |
| 71 | Exploring Language Prior For Mode-Sensitive Visual Attention Modeling | XIAOSHUAI SUN et. al. | In this paper, we propose a new probabilistic framework for attention, and introduce the concept ofmode to model the flexibility and adaptability of attention modulation in complex environments. | CS.mm | 2020-10-12 |
| 72 | BioMegatron: Larger Biomedical Domain Language Model | HOO-CHANG SHIN et. al. | There has been an influx of biomedical domain-specific language models, showing language models pre-trained on biomedical text perform better on biomedical domain benchmarks than those trained on general domain text corpora such as Wikipedia and Books. | CS.arxiv | 2020-10-12 |
| 73 | Boosting Visual Question Answering With Context-aware Knowledge Aggregation | GUOHAO LI et. al. | To solve the challenging issue, we propose a Knowledge Graph Augmented (KG-Aug) model which conducts context-aware knowledge aggregation on external knowledge graphs, requiring no ground-truth knowledge facts for extra supervision. | CS.mm | 2020-10-12 |
| 74 | CM-BERT: Cross-Modal BERT For Text-Audio Sentiment Analysis | KAICHENG YANG et. al. | In this paper, we propose the Cross-Modal BERT (CM-BERT), which relies on the interaction of text and audio modality to fine-tune the pre-trained BERT model. | CS.mm | 2020-10-12 |
| 75 | Contrast And Classify: Alternate Training For Robust VQA | YASH KANT et. al. | We propose a novel training paradigm (ConCAT) that alternately optimizes cross-entropy and contrastive losses. | CS.arxiv | 2020-10-12 |
| 76 | K-armed Bandit Based Multi-Modal Network Architecture Search For Visual Question Answering | YIYI ZHOU et. al. | In this paper, we propose a cross-modal network architecture search (NAS) algorithm for VQA, termed as k-Armed Bandit based NAS (KAB-NAS). | CS.mm | 2020-10-12 |
| 77 | Deep Multimodal Neural Architecture Search | ZHOU YU et. al. | In this paper, we devise a generalized deep multimodal neural architecture search (MMnas) framework for various multimodal learning tasks. | CS.mm | 2020-10-12 |
| 78 | Dual Hierarchical Temporal Convolutional Network With QA-Aware Dynamic Normalization For Video Story Question Answering | FEI LIU et. al. | In this paper, we propose a novel framework named Dual Hierarchical Temporal Convolutional Network (DHTCN) to address the aforementioned defects together. | CS.mm | 2020-10-12 |
| 79 | Gradient-based Analysis Of NLP Models Is Manipulable | JUNLIN WANG et. al. | Gradient-based analysis methods, such as saliency map visualizations and adversarial input perturbations, have found widespread use in interpreting neural NLP models due to their simplicity, flexibility, and most importantly, their faithfulness. | CS.arxiv | 2020-10-11 |
| 81 | Towards Accurate And Reliable Energy Measurement Of NLP Models | QINGQING CAO et. al. | In this work, we show that existing software-based energy measurements are not accurate because they do not take into account hardware differences and how resource utilization affects energy consumption. We release the code and data at https://github.com/csarron/sustainlp2020-energy. | CS.arxiv | 2020-10-11 |
| 82 | Open-Domain Question Answering Goes Conversational Via Question Rewriting | RAVITEJA ANANTHA et. al. | We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 81K question-answer pairs. | CS.arxiv | 2020-10-10 |
| 83 | Localizing Open-Ontology QA Semantic Parsers In A Day Using Machine Translation | MEHRAD MORADSHAHI. GIOVANNI CAMPAGNA et. al. | We propose Semantic Parser Localizer (SPL), a toolkit that leverages Neural Machine Translation (NMT) systems to localize a semantic parser for a new language. | CS.arxiv | 2020-10-10 |
| 84 | On The Importance Of Adaptive Data Collection For Extremely Imbalanced Pairwise Tasks | STEPHEN MUSSMANN et. al. | We instead collect training data with active learning, using a BERT-based embedding model to efficiently retrieve uncertain points from a very large pool of unlabeled utterance pairs. | CS.arxiv | 2020-10-10 |
| 85 | Interpretable Neural Computation For Real-World Compositional Visual Question Answering | RUIXUE TANG et. al. | We aim to combine the two to build an interpretable framework for real-world compositional VQA. | CS.arxiv | 2020-10-10 |
| 86 | Beyond Language: Learning Commonsense From Images For Reasoning | WANQING CUI et. al. | This paper proposes a novel approach to learn commonsense from images, instead of limited raw texts or costly constructed knowledge bases, for the commonsense reasoning problem in NLP. | CS.arxiv | 2020-10-10 |
| 87 | AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data | SILEI XU et. al. | We propose AutoQA, a methodology and toolkit to generate semantic parsers that answer questions on databases, with no manual effort. | CS.arxiv | 2020-10-09 |
| 88 | Relation Extraction As Two-way Span-Prediction | AMIR DN COHEN et. al. | We present a span-prediction based system for RC and evaluate its performance compared to the embedding based system. | CS.arxiv | 2020-10-09 |
| 89 | On The Importance Of Pre-training Data Volume For Compact Language Models | VINCENT MICHELI et. al. | In an effort towards sustainable practices, we study the impact of pre-training data volume on compact language models. | CS.arxiv | 2020-10-08 |
| 90 | Learning To Explain: Datasets And Models For Identifying Valid Reasoning Chains In Multihop Question-Answering | HARSH JHAMTANI et. al. | To address this, we introduce three explanation datasets in which explanations formed from corpus facts are annotated. | CS.arxiv | 2020-10-07 |
| 91 | Improving QA Generalization By Concurrent Modeling Of Multiple Biases | MINGZHU WU et. al. | In this paper, we investigate the impact of debiasing methods for improving generalization and propose a general framework for improving the performance on both in-domain and out-of-domain datasets by concurrent modeling of multiple biases in the training data. | CS.arxiv | 2020-10-07 |
| 92 | Learning A Cost-Effective Annotation Policy For Question Answering | BERNHARD KRATZWALD et. al. | As a remedy, we propose a novel framework for annotating QA datasets that entails learning a cost-effective annotation policy and a semi-supervised annotation scheme. | CS.arxiv | 2020-10-07 |
| 93 | Infusing Disease Knowledge Into BERT For Health Question Answering, Medical Inference And Disease Name Recognition | YUN HE et. al. | Specifically, we propose a new disease knowledge infusion training procedure and evaluate it on a suite of BERT models including BERT, BioBERT, SciBERT, ClinicalBERT, BlueBERT, and ALBERT. | CS.arxiv | 2020-10-07 |
| 94 | MOCHA: A Dataset For Training And Evaluating Generative Reading Comprehension Metrics | ANTHONY CHEN et. al. | To address this, we introduce a benchmark for training and evaluating generative reading comprehension metrics: MOdeling Correctness with Human Annotations. | CS.arxiv | 2020-10-07 |
| 95 | Multi-hop Inference For Question-driven Summarization | YANG DENG et. al. | In this work, we propose a novel question-driven abstractive summarization method, Multi-hop Selective Generator (MSG), to incorporate multi-hop reasoning into question-driven summarization and, meanwhile, provide justifications for the generated summaries. | CS.arxiv | 2020-10-07 |
| 96 | SRLGRN: Semantic Role Labeling Graph Reasoning Network | CHEN ZHENG et. al. | We propose a graph reasoning network based on the semantic structure of the sentences to learn cross paragraph reasoning paths and find the supporting facts and the answer jointly. | CS.arxiv | 2020-10-07 |
| 97 | Cross-Thought For Sentence Encoder Pre-training | SHUOHANG WANG et. al. | In this paper, we propose Cross-Thought, a novel approach to pre-training sequence encoder, which is instrumental in building reusable sequence embeddings for large-scale NLP tasks such as question answering. | CS.arxiv | 2020-10-07 |
| 98 | Vision Skills Needed To Answer Visual Questions | XIAOYU ZENG et. al. | Our first aim is to identify the common vision skills needed for both scenarios. | CS.arxiv | 2020-10-07 |
| 99 | Exposing Shallow Heuristics Of Relation Extraction Models With Challenge Data | SHACHAR ROSENMAN et. al. | We identify failure modes of SOTA relation extraction (RE) models trained on TACRED, which we attribute to limitations in the data annotation process. | CS.arxiv | 2020-10-07 |
| 100 | Unsupervised Evaluation For Question Answering With Transformers | LUKAS MUTTENTHALER et. al. | In this work, we begin by investigating the hidden representations of questions, answers, and contexts in transformer-based QA architectures. | CS.arxiv | 2020-10-07 |
| 101 | Context Modeling With Evidence Filter For Multiple Choice Question Answering | SICHENG YU et. al. | To address the challenge, we propose a simple yet effective approach termed evidence filtering to model the relationships between the encoded contexts with respect to different options collectively and to potentially highlight the evidence sentences and filter out unrelated sentences. | CS.arxiv | 2020-10-06 |
| 102 | BERT Knows Punta Cana Is Not Just Beautiful, It’s Gorgeous: Ranking Scalar Adjectives With Contextualised Representations | AINA GARÍ SOLER et. al. | We propose a novel BERT-based approach to intensity detection for scalar adjectives. | CS.arxiv | 2020-10-06 |
| 103 | DaNetQA: A Yes/no Question Answering Dataset For The Russian Language | TAISIA GLUSHKOVA et. al. | In this paper, we present a reproducible approach to DaNetQA creation and investigate transfer learning methods for task and language transferring. | CS.arxiv | 2020-10-06 |
| 104 | Joint Semantics And Data-Driven Path Representation For Knowledge Graph Inference | GUANGLIN NIU et. al. | To address the above challenges, in this work, we propose a novel joint semantics and data-driven path representation that balances explainability and generalization in the framework of KG embedding. | CS.arxiv | 2020-10-06 |
| 105 | DiPair: Fast And Accurate Distillation For Trillion-Scale Text Matching And Pair Modeling | JIECAO CHEN et. al. | In this work, we propose DiPair — a novel framework for distilling fast and accurate models on text pair tasks. | CS.arxiv | 2020-10-06 |
| 106 | QADiscourse — Discourse Relations As QA Pairs: Representation, Crowdsourcing And Baselines | VALENTINA PYATKIN et. al. | This paper proposes a novel representation of discourse relations as QA pairs, which in turn allows us to crowd-source wide-coverage data annotated with discourse relations, via an intuitively appealing interface for composing such questions and answers. Based on our proposed representation, we collect a novel and wide-coverage QADiscourse dataset, and present baseline algorithms for predicting QADiscourse relations. | CS.arxiv | 2020-10-06 |
| 107 | Universal Natural Language Processing With Limited Annotations: Try Few-shot Textual Entailment As A Start | WENPENG YIN et. al. | In this work, we introduce Universal Few-shot textual Entailment (UFO-Entail). | CS.arxiv | 2020-10-06 |
| 108 | Finding The Evidence: Localization-aware Answer Prediction For Text Visual Question Answering | WEI HAN et. al. | As such, this paper proposes a localization-aware answer prediction network (LaAP-Net) to address this challenge. | CS.arxiv | 2020-10-06 |
| 109 | PolicyQA: A Reading Comprehension Dataset For Privacy Policies | WASI UDDIN AHMAD et. al. | In this paper, we present PolicyQA, a dataset that contains 25,017 reading comprehension style examples curated from an existing corpus of 115 website privacy policies. | CS.arxiv | 2020-10-06 |
| 110 | Efficient Meta Lifelong-Learning With Limited Memory | ZIRUI WANG et. al. | In this paper, we identify three common principles of lifelong learning methods and propose an efficient meta-lifelong framework that combines them in a synergistic fashion. | CS.arxiv | 2020-10-06 |
| 111 | Neural Mask Generator: Learning To Generate Adaptive Word Maskings For Language Model Adaptation | MINKI KANG et. al. | We propose a method to automatically generate a domain- and task-adaptive maskings of the given text for self-supervised pre-training, such that we can effectively adapt the language model to a particular target task (e.g. question answering). | CS.arxiv | 2020-10-06 |
| 112 | PRover: Proof Generation For Interpretable Reasoning Over Rules | SWARNADEEP SAHA et. al. | In our work, we take a step closer to emulating formal theorem provers, by proposing PROVER, an interpretable transformer-based model that jointly answers binary questions over rule-bases and generates the corresponding proofs. | CS.arxiv | 2020-10-06 |
| 113 | Efficient One-Pass End-to-End Entity Linking For Questions | BELINDA Z. LI et. al. | We present ELQ, a fast end-to-end entity linking model for questions, which uses a biencoder to jointly perform mention detection and linking in one pass. | CS.arxiv | 2020-10-05 |
| 114 | Multi-Fact Correction In Abstractive Text Summarization | YUE DONG et. al. | To address this challenge, we propose Span-Fact, a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. | CS.arxiv | 2020-10-05 |
| 115 | InfoBERT: Improving Robustness Of Language Models From An Information Theoretic Perspective | BOXIN WANG et. al. | We aim to address this problem from an information-theoretic perspective, and propose InfoBERT, a novel learning framework for robust fine-tuning of pre-trained language models. | CS.arxiv | 2020-10-05 |
| 116 | UnQovering Stereotyping Biases Via Underspecified Questions | TAO LI et. al. | We present UNQOVER, a general framework to probe and quantify biases through underspecified questions. | CS.arxiv | 2020-10-05 |
| 117 | When In Doubt, Ask: Generating Answerable And Unanswerable Questions, Unsupervised | LIUBOV NIKOLENKO et. al. | A state-of-the-art model based on deep transformers is used to inspect the impact of using synthetic answerable and unanswerable questions to complement a well-known human-made dataset. | CS.arxiv | 2020-10-04 |
| 118 | Attention Guided Semantic Relationship Parsing For Visual Question Answering | MOSHIUR FARAZI et. al. | In this paper, we propose a general purpose semantic relationship parser which generates a semantic feature vector for each subject-predicate-object triplet in an image, and a Mutual and Self Attention (MSA) mechanism that learns to identify relationship triplets that are important to answer the given question. | CS.arxiv | 2020-10-04 |
| 119 | Reading Comprehension As Natural Language Inference: A Semantic Analysis | ANSHUMAN MISHRA et. al. | Therefore, in this paper, we explore the utility of NLI for one of the most prominent downstream tasks, viz. | CS.arxiv | 2020-10-04 |
| 120 | Tell Me How To Ask Again: Question Data Augmentation With Controllable Rewriting In Continuous Space | DAYIHENG LIU et. al. | In this paper, we propose a novel data augmentation method, referred to as Controllable Rewriting based Question Data Augmentation (CRQDA), for machine reading comprehension (MRC), question generation, and question-answering natural language inference tasks. | CS.arxiv | 2020-10-03 |
| 121 | Autoregressive Entity Retrieval | NICOLA DE CAO et. al. | We propose GENRE, the first system that retrieves entities by generating their unique names, left to right, token-by-token in an autoregressive fashion, and conditioned on the context. | CS.arxiv | 2020-10-02 |
| 122 | CAPTION: Correction By Analyses, POS-Tagging And Interpretation Of Objects Using Only Nouns | LEONARDO ANJOLETTO FERREIRA et. al. | This work proposes a combination of DL methods for object detection and natural language processing to validate image’s captions. | CS.arxiv | 2020-10-02 |
| 123 | LUKE: Deep Contextualized Entity Representations With Entity-aware Self-attention | IKUYA YAMADA et. al. | In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. | CS.arxiv | 2020-10-02 |
| 124 | MultiCQA: Zero-Shot Transfer Of Self-Supervised Text Matching Models On A Massive Scale | ANDREAS RÜCKLÉ et. al. | We propose to incorporate self-supervised with supervised multi-task learning on all available source domains. | CS.arxiv | 2020-10-02 |
| 125 | LiveQA: A Question Answering Dataset Over Sports Live | QIANYING LIU et. al. | In this paper, we introduce LiveQA, a new question answering dataset constructed from play-by-play live broadcast. We release the code and data of this paper for future research. | CS.arxiv | 2020-10-01 |
| 126 | Towards Question-Answering As An Automatic Metric For Evaluating The Content Quality Of A Summary | DANIEL DEUTSCH et. al. | In this work, we perform an extensive evaluation of a QA-based metric for summary content quality, calculating its performance with today’s state-of-the-art models as well as estimating its potential upper-bound performance. | CS.arxiv | 2020-10-01 |
| 127 | Interpreting Graph Neural Networks For NLP With Differentiable Edge Masking | MICHAEL SEJR SCHLICHTKRULL et. al. | In this work, we introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. | CS.arxiv | 2020-10-01 |
| 128 | Understanding Tables With Intermediate Pre-training | JULIAN MARTIN EISENSCHLOS et. al. | We adapt TAPAS (Herzig et al., 2020), a table-based BERT model, to recognize entailment. Motivated by the benefits of data augmentation, we create a balanced dataset of millions of automatically created training examples which are learned in an intermediate step prior to fine-tuning. | CS.arxiv | 2020-10-01 |
| 129 | ISAAQ — Mastering Textbook Questions With Pre-trained Transformers And Bottom-Up And Top-Down Attention | JOSE MANUEL GOMEZ-PEREZ et. al. | ISAAQ — Mastering Textbook Questions With Pre-trained Transformers And Bottom-Up And Top-Down Attention | CS.arxiv | 2020-10-01 |
| 130 | Beyond The Text: Analysis Of Privacy Statements Through Syntactic And Semantic Role Labeling | YAN SHVARTZSHNAIDER et. al. | We describe 4 different types of conventional methods that can be partially adapted to address the parameter extraction task with varying degrees of success: Hidden Markov Models, BERT fine-tuned models, Dependency Type Parsing (DP) and Semantic Role Labeling (SRL). | CS.arxiv | 2020-10-01 |
| 131 | Explainable Natural Language Reasoning Via Conceptual Unification | MARCO VALENTINO et. al. | This paper presents an abductive framework for multi-hop and interpretable textual inference. | CS.arxiv | 2020-09-30 |
| 132 | Graph-based Heuristic Search For Module Selection Procedure In Neural Module Network | YUXUAN WU et. al. | In consideration of this, we proposed a new learning framework for NMN. | CS.arxiv | 2020-09-30 |
| 133 | A Vietnamese Dataset For Evaluating Machine Reading Comprehension | KIET VAN NGUYEN et. al. | In particular, we propose a new process of dataset creation for Vietnamese MRC. Due to the lack of benchmark datasets for Vietnamese, we present the Vietnamese Question Answering Dataset (ViQuAD), a new dataset for the low-resource language as Vietnamese to evaluate MRC models. | CS.arxiv | 2020-09-30 |
| 134 | Bridging Information-Seeking Human Gaze And Machine Reading Comprehension | JONATHAN MALMAUD et. al. | In this work, we analyze how human gaze during reading comprehension is conditioned on the given reading comprehension question, and whether this signal can be beneficial for machine reading comprehension. To this end, we collect a new eye-tracking dataset with a large number of participants engaging in a multiple choice reading comprehension task. | CS.arxiv | 2020-09-30 |
| 135 | Stochastic Precision Ensemble: Self-Knowledge Distillation For Quantized Deep Neural Networks | YOONHO BOO et. al. | In this study, we propose stochastic precision ensemble training for QDNNs (SPEQ). | CS.arxiv | 2020-09-30 |
| 136 | Neural Retrieval For Question Answering With Cross-Attention Supervised Data Augmentation | YINFEI YANG et. al. | We present a supervised data mining method using an accurate early fusion model to improve the training of an efficient late fusion retrieval model. | CS.arxiv | 2020-09-29 |
| 137 | A Survey On Semantic Parsing From The Perspective Of Compositionality | PAWAN KUMAR et. al. | In the following section after an introduction of the field of semantic parsing and its uses in KBQA, we will describe meaning representation using grammar formalism CCG (Steedman, 1996). | CS.arxiv | 2020-09-29 |
| 138 | Sequence-to-Sequence Learning For Indonesian Automatic Question Generator | FERDIANT JOSHUA MUIS et. al. | In this work we construct an Indonesian automatic question generator, adapting the architecture from some previous works. | CS.arxiv | 2020-09-29 |
| 139 | MaP: A Matrix-based Prediction Approach To Improve Span Extraction In Machine Reading Comprehension | HUAISHAO LUO et. al. | In this paper, we propose a novel approach that extends the probability vector to a probability matrix. | CS.arxiv | 2020-09-29 |
| 140 | What Disease Does This Patient Have? A Large-scale Open Domain Question Answering Dataset From Medical Exams | DI JIN et. al. | In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical problems, MedQA, collected from the professional medical board exams. | CS.arxiv | 2020-09-28 |
| 141 | Hierarchical Deep Multi-modal Network For Medical Visual Question Answering | DEEPAK GUPTA et. al. | We evaluate the performance of our proposed model on two benchmark datasets, viz. | CS.arxiv | 2020-09-27 |
| 142 | Unsupervised Pre-training For Biomedical Question Answering | VAISHNAVI KOMMARAJU et. al. | To further improve unsupervised representations for biomedical QA, we introduce a new pre-training task from unlabeled data designed to reason about biomedical entities in the context. | CS.arxiv | 2020-09-27 |
| 143 | SPARTA: Efficient Open-Domain Question Answering Via Sparse Transformer Matching Retrieval | TIANCHENG ZHAO et. al. | We introduce SPARTA, a novel neural retrieval method that shows great promise in performance, generalization, and interpretability for open-domain question answering. | CS.arxiv | 2020-09-27 |
| 144 | KG-BART: Knowledge Graph-Augmented BART For Generative Commonsense Reasoning | YE LIU et. al. | To promote the ability of commonsense reasoning for text generation, we propose a novel knowledge graphaugmented pre-trained language generation model KG-BART, which encompasses the complex relations of concepts through the knowledge graph and produces more logical and natural sentences as output. | CS.arxiv | 2020-09-26 |
| 145 | Techniques To Improve Q&A Accuracy With Transformer-based Models On Large Complex Documents | CHEJUI LIAO et. al. | This paper takes a scientific approach to determine the benefits and effectiveness of various techniques and concludes a best-fit combination that produces a statistically significant improvement in accuracy. | CS.arxiv | 2020-09-26 |
| 146 | XTE: Explainable Text Entailment | VIVIAN S. SILVA et. al. | In this work, we introduce XTE – Explainable Text Entailment – a novel composite approach for recognizing text entailment which analyzes the entailment pair to decide whether it must be resolved syntactically or semantically. | CS.arxiv | 2020-09-25 |
| 147 | Machine Knowledge: Creation And Curation Of Comprehensive Knowledge Bases | GERHARD WEIKUM et. al. | To support the long-term life-cycle and the quality assurance of machine knowledge, the article presents methods for constructing open schemas and for knowledge curation. | CS.arxiv | 2020-09-24 |
| 148 | AliMe KG: Domain Knowledge Graph Construction And Application In E-commerce | FENG-LIN LI et. al. | In the paper, we systematically introduce how we construct domain knowledge graph from free text, and demonstrate its business value with several applications. | CS.arxiv | 2020-09-24 |
| 149 | X-LXMERT: Paint, Caption And Answer Questions With Multi-Modal Transformers | JAEMIN CHO et. al. | We introduce X-LXMERT, an extension to LXMERT with training refinements including: discretizing visual representations, using uniform masking with a large range of masking ratios and aligning the right pre-training datasets to the right objectives which enables it to paint. | CS.arxiv | 2020-09-23 |
| 150 | Multiple Interaction Learning With Question-type Prior Knowledge For Constraining Answer Search Space In Visual Question Answering | TUONG DO et. al. | In this paper, we propose a novel VQA model that utilizes the question-type prior information to improve VQA by leveraging the multiple interactions between different joint modality methods based on their behaviors in answering questions from different types. | CS.arxiv | 2020-09-23 |
| 151 | Using The Hammer Only On Nails: A Hybrid Method For Evidence Retrieval For Question Answering | ZHENGZHONG LIANG et. al. | Learning from this probing analysis, we introduce a hybrid approach for evidence retrieval that combines the advantages of both IR directions. | CS.arxiv | 2020-09-22 |
| 152 | SQuARE: Semantics-based Question Answering And Reasoning Engine | KINJAL BASU et. al. | A question posed against that text is converted into an ASP query using the same framework and executed using the s(CASP) goal-directed ASP system. | CS.arxiv | 2020-09-21 |
| 153 | Regularizing Attention Networks For Anomaly Detection In Visual Question Answering | DOYUP LEE et. al. | In this study, we evaluate the robustness of state-of-the-art VQA models to five different anomalies, including worst-case scenarios, the most frequent scenarios, and the current limitation of VQA models. | CS.arxiv | 2020-09-21 |
| 155 | UCD-CS At W-NUT 2020 Shared Task-3: A Text To Text Approach For COVID-19 Event Extraction On Social Media | CONGCONG WANG et. al. | In this paper, we describe our approach in the shared task: COVID-19 event extraction from Twitter. | CS.arxiv | 2020-09-21 |
| 156 | Can Questions Summarize A Corpus? Using Question Generation For Characterizing COVID-19 Research | GABRIELA SURITA et. al. | In this work, we investigate using question generation models for exploring a collection of documents. | CS.arxiv | 2020-09-19 |
| 157 | Tradeoffs In Sentence Selection Techniques For Open-Domain Question Answering | SHIH-TING LIN et. al. | In this paper, we focus on approaches which apply an intermediate sentence selection step to address this issue, and investigate the best practices for this approach. | CS.arxiv | 2020-09-18 |
| 158 | Looking Beyond Sentence-Level Natural Language Inference For Downstream Tasks | ANSHUMAN MISHRA et. al. | In this paper, we study this unfulfilled promise from the lens of two downstream tasks: question answering (QA), and text summarization. | CS.arxiv | 2020-09-18 |
| 159 | A Multimodal Memes Classification: A Survey And Open Research Issues | TARIQ HABIB AFRIDI et. al. | We propose a generalized framework for VL problems. | CS.arxiv | 2020-09-17 |
| 160 | On The Transferability Of Minimal Prediction Preserving Inputs In Question Answering | SHAYNE LONGPRE et. al. | Recent work (Feng et al., 2018) establishes the presence of short, uninterpretable input fragments that yield high confidence and accuracy in neural models. | CS.arxiv | 2020-09-17 |
| 161 | Compositional And Lexical Semantics In RoBERTa, BERT And DistilBERT: A Case Study On CoQA | IEVA STALIŪNAITĖ et. al. | We identify the problematic areas for the finetuned RoBERTa, BERT and DistilBERT models through systematic error analysis – basic arithmetic (counting phrases), compositional semantics (negation and Semantic Role Labeling), and lexical semantics (surprisal and antonymy). | CS.arxiv | 2020-09-17 |
| 162 | Generation-Augmented Retrieval For Open-domain Question Answering | YUNING MAO et. al. | In this paper, we present Generation-Augmented Retrieval (GAR), a query expansion method that augments a query with relevant contexts through text generation. | CS.arxiv | 2020-09-17 |
| 163 | MUTANT: A Training Paradigm For Out-of-Distribution Generalization In Visual Question Answering | TEJAS GOKHALE et. al. | In this paper, we present MUTANT, a training paradigm that exposes the model to perceptually similar, yet semantically distinct mutations of the input, to improve OOD generalization, such as the VQA-CP challenge. | CS.arxiv | 2020-09-17 |
| 164 | ISCAS At SemEval-2020 Task 5: Pre-trained Transformers For Counterfactual Statement Modeling | YAOJIE LU et. al. | This paper describes our system which is based on pre-trained transformers. | CS.arxiv | 2020-09-17 |
| 165 | Multi-modal Summarization For Video-containing Documents | XIYAN FU et. al. | Hence, we propose a novel multi-modal summarization task to summarize from a document and its associated video. Moreover, we collect a novel dataset and it provides a new resource for future study that results from documents and videos. | CS.arxiv | 2020-09-16 |
| 166 | Self-supervised Pre-training And Contrastive Representation Learning For Multiple-choice Video QA | SEONHOON KIM et. al. | In this paper, we propose novel training schemes for multiple-choice video question answering with a self-supervised pre-training stage and a supervised contrastive learning in the main stage as an auxiliary learning. | CS.arxiv | 2020-09-16 |
| 167 | DDRQA: Dynamic Document Reranking For Open-domain Multi-hop Question Answering | YUYU ZHANG et. al. | To address this challenge, we propose Dynamic Document Reranking (DDR) to iteratively retrieve, rerank and filter documents, and adaptively determine when to stop the retrieval process. | CS.arxiv | 2020-09-16 |
| 168 | Leveraging Semantic Parsing For Relation Linking Over Knowledge Bases | NANDANA MIHINDUKULASOORIYA et. al. | To overcome these challenges, we present SLING, a relation linking framework which leverages semantic parsing using Abstract Meaning Representation (AMR) and distant supervision. | CS.arxiv | 2020-09-16 |
| 169 | Knowledge Graphs For Multilingual Language Translation And Generation | DIEGO MOUSSALLEM | In this thesis, we focus on the use of KGs for machine translation and the generation of texts to deal with the problems caused by entities and consequently enhance the quality of automatically generated texts. | CS.arxiv | 2020-09-16 |
| 170 | Receptivity Of An AI Cognitive Assistant By The Radiology Community: A Report On Data Collected At RSNA | KARINA KANJARIA et. al. | In this paper, the methodology of the survey is shown and a summary of its results are presented. | CS.arxiv | 2020-09-13 |
| 171 | Cluster-Former: Clustering-based Sparse Transformer For Long-Range Dependency Encoding | SHUOHANG WANG et. al. | In this paper, we propose Cluster-Former, a novel clustering-based sparse Transformer to perform attention across chunked sequences. | CS.arxiv | 2020-09-13 |
| 172 | A Simple And Efficient Framework For Identifying Relation-gaps In Ontologies | SUBHASHREE S et. al. | We address the above question in this paper. | CS.arxiv | 2020-09-12 |
| 173 | An Atlas Of Cultural Commonsense For Machine Reasoning | ANURAG ACHARYA et. al. | In this work, we introduce an approach that extends prior work on crowdsourcing commonsense knowledge by incorporating differences in knowledge that are attributable to cultural or national groups. | CS.arxiv | 2020-09-11 |
| 174 | FILTER: An Enhanced Fusion Method For Cross-lingual Language Understanding | YUWEI FANG et. al. | In this paper, we propose FILTER, an enhanced fusion method that takes cross-lingual data as input for XLM finetuning. | CS.arxiv | 2020-09-10 |
| 175 | Accelerating Real-Time Question Answering Via Question Generation | YUWEI FANG et. al. | To accelerate RTQA for practical use, we present Ocean-Q (an Ocean of Questions), a novel approach that leverages question generation (QG) for RTQA. | CS.arxiv | 2020-09-10 |
| 176 | Sanitizing Synthetic Training Data Generation For Question Answering Over Knowledge Graphs | TROND LINJORDET et. al. | Synthetic data generation is important to training and evaluating neural models for question answering over knowledge graphs. | CS.arxiv | 2020-09-10 |
| 177 | Aspect Classification For Legal Depositions | SAURABH CHAKRAVARTY et. al. | We hypothesize that a legal deposition consists of various aspects that are discussed as part of the deponent testimony. | CS.arxiv | 2020-09-09 |
| 178 | E-BERT: A Phrase And Product Knowledge Enhanced Language Model For E-commerce | DENGHUI ZHANG et. al. | To tackle the problem, we propose a unified pre-training framework, namely, E-BERT. | CS.arxiv | 2020-09-06 |
| 179 | KILT: A Benchmark For Knowledge Intensive Language Tasks | FABIO PETRONI et. al. | To catalyze research on models that condition on specific information in large textual resources, we present a benchmark for knowledge-intensive language tasks (KILT). | CS.arxiv | 2020-09-04 |
| 180 | Multi-Perspective Semantic Information Retrieval | SAMARTH RAWAL et. al. | This work introduces the concept of a Multi-Perspective IR system, a novel methodology that combines multiple deep learning and traditional IR models to better predict the relevance of a query-sentence pair, along with a standardized framework for tuning this system. | CS.arxiv | 2020-09-03 |
| 181 | A Comparison Of Pre-trained Vision-and-Language Models For Multimodal Representation Learning Across Medical Images And Reports | YIKUAN LI et. al. | In this study, we adopt four pre-trained V+L models: LXMERT, VisualBERT, UNIER and PixelBERT to learn multimodal representation from MIMIC-CXR radiographs and associated reports. | CS.arxiv | 2020-09-03 |
| 182 | Revisiting The Open-Domain Question Answering Pipeline | SINA J. SEMNANI et. al. | This paper describes Mindstone, an open-domain QA system that consists of a new multi-stage pipeline that employs a traditional BM25-based information retriever, RM3-based neural relevance feedback, neural ranker, and a machine reading comprehension stage. | CS.arxiv | 2020-09-02 |
| 183 | Text Modular Networks: Learning To Decompose Tasks In The Language Of Existing Models | TUSHAR KHOT et. al. | We propose a general approach, Text Modular Networks(TMNs), where the system learns to decompose any complex task into the language of existing models. | CS.arxiv | 2020-09-01 |
| 184 | PNEL: Pointer Network Based End-To-End Entity Linking Over Knowledge Graphs | DEBAYAN BANERJEE et. al. | In this work we present a novel approach to end-to-end EL by applying the popular Pointer Network model, which achieves competitive performance. | CS.arxiv | 2020-08-31 |
| 185 | Cross-modal Knowledge Reasoning For Knowledge-based Visual Question Answering | JING YU et. al. | Inspired by the human cognition theory, in this paper, we depict an image by multiple knowledge graphs from the visual, semantic and factual views. | CS.arxiv | 2020-08-31 |
| 186 | Classifier Combination Approach For Question Classification For Bengali Question Answering System | SOMNATH BANERJEE et. al. | We have exploited state-of-the-art multiple model combination techniques, i.e., ensemble, stacking and voting, to increase QC accuracy. | CS.arxiv | 2020-08-31 |
| 187 | A Dataset And Baselines For Visual Question Answering On Art | NOA GARCIA et. al. | In this work, we introduce our first attempt towards building a new dataset, coined AQUA (Art QUestion Answering). | CS.arxiv | 2020-08-28 |
| 188 | AllenAct: A Framework For Embodied AI Research | LUCA WEIHS et. al. | We introduce AllenAct, a modular and flexible learning framework designed with a focus on the unique requirements of Embodied AI research. | CS.arxiv | 2020-08-28 |
| 189 | Rethinking The Objectives Of Extractive Question Answering | MARTIN FAJCIK et. al. | This paper describes two generally applicable approaches towards the significant improvement of the performance of state-of-the-art extractive question answering (EQA) systems. | CS.arxiv | 2020-08-28 |
| 190 | Visual Question Answering On Image Sets | ANKAN BANSAL et. al. | We introduce the task of Image-Set Visual Question Answering (ISVQA), which generalizes the commonly studied single-image VQA problem to multi-image settings. To enable research in this new topic, we introduce two ISVQA datasets – indoor and outdoor scenes. | CS.arxiv | 2020-08-27 |
| 191 | Relation/Entity-Centric Reading Comprehension | TAKESHI ONISHI | More specifically, we focus on question answering tasks designed to measure reading comprehension. | CS.arxiv | 2020-08-27 |
| 192 | Example-Based Named Entity Recognition | MORTEZA ZIYADI et. al. | We present a novel approach to named entity recognition (NER) in the presence of scarce data that we call example-based NER. | CS.arxiv | 2020-08-24 |
| 193 | Quantum Language Model With Entanglement Embedding For Question Answering | YIWEI CHEN et. al. | We propose a neural network model with a novel Entanglement Embedding (EE) module, whose function is to transform the word sequences into entangled pure states of many-body quantum systems. | CS.arxiv | 2020-08-22 |
| 194 | Data Augmentation Techniques For The Video Question Answering Task | ALEX FALCON et. al. | To alleviate this problem, we propose several augmentation techniques which give us a +5.5% improvement on the final accuracy over the considered baseline. | CS.arxiv | 2020-08-22 |
| 195 | Reducing Language Biases In Visual Question Answering With Visually-Grounded Question Encoder | GOUTHAMAN KV et. al. | In this work, we propose a novel model-agnostic question encoder, Visually-Grounded Question Encoder (VGQE), for VQA that reduces this effect. | CS.eccv | 2020-08-21 |
| 196 | Large-scale Pretraining For Visual Dialog: A Simple State-of-the-Art Baseline | VISHVAK MURAHARI et. al. | Instead, we present an approach to leverage pretraining on related vision-language datasets before transferring to visual dialog. | CS.eccv | 2020-08-21 |
| 197 | AutoKnow: Self-Driving Knowledge Collection For Products Of Thousands Of Types | XIN LUNA DONG et. al. | We describe AutoKnow, our automatic (self-driving) system that addresses these challenges. | CS.kdd | 2020-08-21 |
| 198 | Visual Relation Grounding In Videos | JUNBIN XIAO et. al. | In this paper, we explore a novel task named visual Relation Grounding in Videos (vRGV). | CS.eccv | 2020-08-21 |
| 199 | Learning What Makes A Difference From Counterfactual Examples And Gradient Supervision | DAMIEN TENEY et. al. | We propose an auxiliary training objective that improves the generalization capabilities of neural networks by leveraging an overlooked supervisory signal found in existing datasets. | CS.eccv | 2020-08-21 |
| 200 | Knowledge-Based Video Question Answering With Unsupervised Scene Descriptions | NOA GARCIA et. al. | Inspired by this behaviour, we design ROLL, a model for knowledge-based video story question answering that leverages three crucial aspects of movie understanding: dialog comprehension, scene reasoning, and storyline recalling. | CS.eccv | 2020-08-21 |
| 201 | VQA-LOL: Visual Question Answering Under The Lens Of Logic | TEJAS GOKHALE et. al. | In this paper, we investigate whether visual question answering (VQA) systems trained to answer a question about an image, are able to answer the logical composition of multiple such questions. | CS.eccv | 2020-08-21 |
| 202 | Learning To Extract Attribute Value From Product Via Question Answering: A Multi-task Approach | QIFAN WANG et. al. | In this work, we propose a novel approach for Attribute Value Extraction via Question Answering (AVEQA) using a multi-task framework. | CS.kdd | 2020-08-21 |
| 203 | UNITER: UNiversal Image-TExt Representation Learning | YEN-CHUN CHEN et. al. | In this paper, we introduce UNITER, a UNiversal Image-TExt Representation, learned through large-scale pre-training over four image-text datasets (COCO, Visual Genome, Conceptual Captions, and SBU Captions), which can power heterogeneous downstream V+L tasks with joint multimodal embeddings. | CS.eccv | 2020-08-21 |
| 204 | Interpretable Visual Reasoning Via Probabilistic Formulation Under Natural Supervision | XINZHE HAN et. al. | In this paper, we rethink implicit reasoning process in VQA, and propose a new formulation which maximizes the log-likelihood of joint distribution for the observed question and predicted answer. | CS.eccv | 2020-08-21 |
| 205 | A Competence-aware Curriculum For Visual Concepts Learning Via Question Answering | QING LI et. al. | To mimic this efficient learning ability, we propose a competence-aware curriculum for visual concept learning in a question-answering manner. | CS.eccv | 2020-08-21 |
| 206 | Effective Transfer Learning For Identifying Similar Questions: Matching User Questions To COVID-19 FAQs | CLARA H. MCCREERY et. al. | In this paper, we show how a double fine-tuning approach of pretraining a neural network on medical question-answer pairs followed by fine-tuning on medical question-question pairs is a particularly useful intermediate task for the ultimate goal of determining medical question similarity. | CS.kdd | 2020-08-21 |
| 207 | TRRNet: Tiered Relation Reasoning For Compositional Visual Question Answering | XIAOFENG YANG et. al. | We propose a novel tiered reasoning method that dynamically selects object level candidates based on language representations and generates robust pairwise relations within the selected candidate objects. | CS.eccv | 2020-08-21 |
| 208 | Semantic Equivalent Adversarial Data Augmentation For Visual Question Answering | RUIXUE TANG et. al. | In this paper, instead of directly manipulating images and questions, we use generated adversarial examples for both images and questions as the augmented data. | CS.eccv | 2020-08-21 |
| 209 | REMIND Your Neural Network To Prevent Catastrophic Forgetting | TYLER L. HAYES et. al. | Here, we propose REMIND, a brain-inspired approach that enables efficient replay with compressed representations. | CS.eccv | 2020-08-21 |
| 210 | Multi-Agent Embodied Question Answering In Interactive Environments | SINAN TAN et. al. | We investigate a new AI task — Multi-Agent Interactive Question Answering — where several agents explore the scene jointly in interactive environments to answer a question. | CS.eccv | 2020-08-21 |
| 211 | Mining Implicit Relevance Feedback From User Behavior For Web Question Answering | LINJUN SHOU et. al. | In this paper, we make the first study to explore the correlation between user behavior and passage relevance, and propose a novel approach for mining training data for Web QA. | CS.kdd | 2020-08-21 |
| 212 | Privacy Policies Over Time: Curation And Analysis Of A Million-Document Dataset | RYAN AMOS et. al. | Automated analysis of privacy policies has proved a fruitful research direction, with developments such as automated policy summarization, question answering systems, and compliance detection. | CS.arxiv | 2020-08-20 |
| 213 | Document Visual Question Answering Challenge 2020 | MINESH MATHEW et. al. | This paper presents results of Document Visual Question Answering Challenge organized as part of Text and Documents in the Deep Learning Era workshop, in CVPR 2020. | CS.arxiv | 2020-08-20 |
| 214 | Commonsense Knowledge In Wikidata | FILIP ILIEVSKI et. al. | Based on these findings, we propose three recommended actions to improve the coverage and quality of Wikidata-CS further. | CS.arxiv | 2020-08-18 |
| 215 | Describing Unseen Videos Via Multi-Modal Cooperative Dialog Agents | YE ZHU et. al. | To this end, in this paper, we introduce a new task called video description via two multi-modal cooperative dialog agents, whose ultimate goal is for one conversational agent to describe an unseen video based on the dialog and two static frames. | CS.arxiv | 2020-08-18 |
| 216 | An Annotated Corpus Of Webtables For Information Extraction Tasks | ERIN MACDONALD et. al. | 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. | CS.arxiv | 2020-08-17 |
| 217 | Fine-Grained Relevance Annotations For Multi-Task Document Ranking And Question Answering | SEBASTIAN HOFSTÄTTER et. al. | In this work, we present FiRA: a novel dataset of Fine-Grained Relevance Annotations. | CS.arxiv | 2020-08-12 |
| 218 | Assisting Scene Graph Generation With Self-Supervision | SANDEEP INUGANTI et. al. | We propose a set of three novel yet simple self-supervision tasks and train them as auxiliary multi-tasks to the main model. | CS.arxiv | 2020-08-08 |
| 219 | Question And Answer Test-Train Overlap In Open-Domain Question Answering Datasets | PATRICK LEWIS et. al. | In this work, we perform a detailed study of the test sets of three popular open-domain benchmark datasets with respect to these competencies. | CS.arxiv | 2020-08-06 |
| 220 | Interpretable Multi-Step Reasoning With Knowledge Extraction On Complex Healthcare Question Answering | YE LIU et. al. | In order to solve this challenging task, we present a Multi-step reasoning with Knowledge extraction framework (MurKe). | CS.arxiv | 2020-08-05 |
| 221 | Video Question Answering On Screencast Tutorials | WENTIAN ZHAO et. al. | This paper presents a new video question answering task on screencast tutorials. We introduce a dataset including question, answer and context triples from the tutorial videos for a software. | CS.arxiv | 2020-08-02 |
| 222 | Trojaning Language Models For Fun And Profit | XINYANG ZHANG et. al. | Specifically, we present TROJAN-ML, a new class of trojaning attacks in which maliciously crafted LMs trigger host NLP systems to malfunction in a highly predictable manner. | CS.arxiv | 2020-08-01 |
| 223 | MKQA: A Linguistically Diverse Benchmark For Multilingual Open Domain Question Answering | SHAYNE LONGPRE et. al. | We introduce Multilingual Knowledge Questions and Answers (MKQA), an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). | CS.arxiv | 2020-07-29 |
| 224 | NeuralQA: A Usable Library For Question Answering (Contextual Query Expansion + BERT) On Large Datasets | VICTOR DIBIA | To help address these issues, we introduce NeuralQA – a usable library for QA on large datasets. | CS.arxiv | 2020-07-29 |
| 225 | Big Bird: Transformers For Longer Sequences | MANZIL ZAHEER et. al. | To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear. | CS.arxiv | 2020-07-28 |
| 226 | A Survey On Complex Question Answering Over Knowledge Base: Recent Advances And Challenges | BIN FU et. al. | After describing the methods of these branches, we analyze directions for future research and introduce the models proposed by the Alime team. | CS.arxiv | 2020-07-26 |
| 227 | REXUP: I REason, I EXtract, I UPdate With Structured Compositional Reasoning For Visual Question Answering | SIWEN LUO et. al. | In this paper, we propose a deep reasoning VQA model with explicit visual structure-aware textual information, and it works well in capturing step-by-step reasoning process and detecting a complex object-relationship in photo-realistic images. | CS.arxiv | 2020-07-26 |
| 228 | Efficient Document Re-Ranking For Transformers By Precomputing Term Representations | SEAN MACAVANEY et. al. | Our proposed approach, called PreTTR (Precomputing Transformer Term Representations), considerably reduces the query-time latency of deep transformer networks (up to a 42x speedup on web document ranking) making these networks more practical to use in a real-time ranking scenario. | CS.sigir | 2020-07-25 |
| 229 | Incorporating User Feedback In Conversational Question Answering Over Heterogeneous Web Sources | MAGDALENA KAISER | This PhD thesis will explore conversational question answering with a special emphasis on incorporating user feedback. | CS.sigir | 2020-07-25 |
| 230 | DC-BERT: Decoupling Question And Document For Efficient Contextual Encoding | PING NIE et. al. | To address the efficiency problem, we propose DC-BERT, a decoupled contextual encoding framework that has dual BERT models: an online BERT which encodes the question only once, and an offline BERT which pre-encodes all the documents and caches their encodings. | CS.sigir | 2020-07-25 |
| 231 | Conversational Question Answering Over Passages By Leveraging Word Proximity Networks | MAGDALENA KAISER et. al. | In this work, we demonstrate CROWN (Conversational passage ranking by Reasoning Over Word Networks): an unsupervised yet effective system for conversational QA with passage responses, that supports several modes of context propagation over multiple turns. | CS.sigir | 2020-07-25 |
| 232 | The Cortical Activity Of Graded Relevance | ZUZANA PINKOSOVA et. al. | In this paper, we aim to investigate the brain activity associated with relevance when it is treated as a graded concept. | CS.sigir | 2020-07-25 |
| 233 | User-Inspired Posterior Network For Recommendation Reason Generation | HAOLAN ZHAN et. al. | Therefore, in this paper, we consider generating the recommendation reason by taking into account not only the product attributes but also the customer-generated product QA discussions. | CS.sigir | 2020-07-25 |
| 234 | Open-Retrieval Conversational Question Answering | CHEN QU et. al. | To address this limitation, we introduce an open-retrieval conversational question answering (ORConvQA) setting, where we learn to retrieve evidence from a large collection before extracting answers, as a further step towards building functional conversational search systems. | CS.sigir | 2020-07-25 |
| 235 | Large-scale Multi-modal Search And QA At Alibaba | RONG JIN | In this talk, we will present ongoing efforts of Alibaba on large-scale multi-modal search ad question-answering, including image search, video search, cross lingual retrieval, and QA based on machine reading and comprehension (MRC). | CS.sigir | 2020-07-25 |
| 236 | Multi-Document Answer Generation For Non-Factoid Questions | VALERIIA BARANOVA-BOLOTOVA | The current research will be devoted to the challenging and under-investigated task of multi-source answer generation for complex non-factoid questions. | CS.sigir | 2020-07-25 |
| 237 | Macaw: An Extensible Conversational Information Seeking Platform | HAMED ZAMANI et. al. | This paper introduces Macaw, an open-source framework with a modular architecture for CIS research. | CS.sigir | 2020-07-25 |
| 238 | Deep Neural Matching Models For Graph Retrieval | KUNAL GOYAL et. al. | In this paper, we present an effective, feature and structure-aware, end-to-end trainable neural match scoring system for graphs. | CS.sigir | 2020-07-25 |
| 239 | Having Your Cake And Eating It Too: Training Neural Retrieval For Language Inference Without Losing Lexical Match | VIKAS YADAV et. al. | To mitigate this limitation, we introduce a supervised RoBERTa QA method that is trained to mimic the behavior of BM25 and the soft-matching idea behind embedding-based alignment methods. | CS.sigir | 2020-07-25 |
| 240 | Bridging Hierarchical And Sequential Context Modeling For Question-driven Extractive Answer Summarization | YANG DENG et. al. | In this paper, we propose a unified model to bridge hierarchical and sequential context modeling for question-driven extractive answer summarization. | CS.sigir | 2020-07-25 |
| 241 | Residual-Duet Network With Tree Dependency Representation For Chinese Question-Answering Sentiment Analysis | GUANGYI HU et. al. | In this work, we propose a Residual-Duet Network leveraging textual and tree dependency information for Chinese question-answering sentiment analysis. | CS.sigir | 2020-07-25 |
| 242 | Humor Detection In Product Question Answering Systems | YFTAH ZISER et. al. | In this study we present a deep-learning framework for detecting humorous questions in PQA systems. | CS.sigir | 2020-07-25 |
| 243 | Match²: A Matching Over Matching Model For Similar Question Identification | ZIZHEN WANG et. al. | In this work, we propose atwo-side usage, which leverages the answer as a bridge of the two questions. | CS.sigir | 2020-07-25 |
| 244 | Incorporating Scenario Knowledge Into A Unified Fine-tuning Architecture For Event Representation | JIANMING ZHENG et. al. | In this paper, we propose a unified fine-tuning architecture, incorporated with scenario knowledge for event representation, i.e., UniFA-S, which mainly consists of a unified fine-tuning architecture (UniFA) and a scenario-level variational auto-encoder (S-VAE). | CS.sigir | 2020-07-25 |
| 245 | Investigating Reading Behavior In Fine-grained Relevance Judgment | ZHIJING WU et. al. | To shed light on this research question, we investigate how users allocate their attention to passages of a document during the relevance judgment process. | CS.sigir | 2020-07-25 |
| 246 | Answer Ranking For Product-Related Questions Via Multiple Semantic Relations Modeling | WENXUAN ZHANG et. al. | In this paper, we investigate the answer ranking problem for product-related questions, with the relevant reviews treated as auxiliary information that can be exploited for facilitating the ranking. | CS.sigir | 2020-07-25 |
| 247 | QuAChIE: Question Answering Based Chinese Information Extraction System | DONGYU RU et. al. | In this paper, we present the design of QuAChIE, a Question Answering based Chinese Information Extraction system. For the training and evaluation of each model in the system, we build a large-scale information extraction dataset using Wikidata and Wikipedia pages by distant supervision. | CS.sigir | 2020-07-25 |
| 248 | Reranking For Efficient Transformer-based Answer Selection | YOSHITOMO MATSUBARA et. al. | In this paper, we show that standard and efficient neural rerankers can be used to reduce the amount of sentence candidates fed to Transformer models without hurting Accuracy, thus improving efficiency up to four times. | CS.sigir | 2020-07-25 |
| 249 | A Survey On Graph Neural Networks For Knowledge Graph Completion | SIDDHANT ARORA | In this survey, we understand the various strengths and weaknesses of the proposed methodology and try to find new exciting research problems in this area that require further investigation. | CS.arxiv | 2020-07-24 |
| 250 | Better Early Than Late: Fusing Topics With Word Embeddings For Neural Question Paraphrase Identification | NICOLE PEINELT et. al. | We therefore propose two ways of merging topics with word embeddings (early vs. late fusion) in a new neural architecture for question paraphrase identification. | CS.arxiv | 2020-07-22 |
| 251 | EndCold: An End-to-End Framework For Cold Question Routing In Community Question Answering Services | JIANKAI SUN et. al. | Therefore, we propose to address the challenge of leveraging heterogeneous graph and textual information for cold question routing by designing an end-to-end framework that jointly learns CQA node embeddings and finds best answerers for cold questions. | CS.ijcai | 2020-07-21 |
| 252 | Retrieve, Program, Repeat: Complex Knowledge Base Question Answering Via Alternate Meta-learning | YUNCHENG HUA et. al. | In this paper, we present a novel method that automatically learns a retrieval model alternately with the programmer from weak supervision, i.e., the system’s performance with respect to the produced answers. | CS.ijcai | 2020-07-21 |
| 253 | Effective Search Of Logical Forms For Weakly Supervised Knowledge-Based Question Answering | TAO SHEN et. al. | In this work, we propose an effective search method for weakly supervised KBQA based on operator prediction for questions. | CS.ijcai | 2020-07-21 |
| 254 | ERNIE-GEN: An Enhanced Multi-Flow Pre-training And Fine-tuning Framework For Natural Language Generation | DONGLING XIAO et. al. | To address this issue, we propose an enhanced multi-flow sequence to sequence pre-training and fine-tuning framework named ERNIE-GEN, which bridges the discrepancy between training and inference with an infilling generation mechanism and a noise-aware generation method. | CS.ijcai | 2020-07-21 |
| 255 | Two-Phase Hypergraph Based Reasoning With Dynamic Relations For Multi-Hop KBQA | JIALE HAN et. al. | Inspired by human’s hop-by-hop reasoning, we propose an interpretable KBQA model based on DHGCN, namely two-phase hypergraph based reasoning with dynamic relations, which explicitly updates relation information and dynamically pays attention to different relations at different hops. | CS.ijcai | 2020-07-21 |
| 256 | Mucko: Multi-Layer Cross-Modal Knowledge Reasoning For Fact-based Visual Question Answering | ZIHAO ZHU et. al. | In this paper, we depict an image by a multi-modal heterogeneous graph, which contains multiple layers of information corresponding to the visual, semantic and factual features. | CS.ijcai | 2020-07-21 |
| 257 | Formal Query Building With Query Structure Prediction For Complex Question Answering Over Knowledge Base | YONGRUI CHEN et. al. | In this paper, we propose a new formal query building approach that consists of two stages. | CS.ijcai | 2020-07-21 |
| 258 | Learning To Discretely Compose Reasoning Module Networks For Video Captioning | GANCHAO TAN et. al. | In this paper, we propose a novel visual reasoning approach for video captioning, named Reasoning Module Networks (RMN), to equip the existing encoder-decoder framework with the above reasoning capacity. | CS.ijcai | 2020-07-21 |
| 259 | Feature Augmented Memory With Global Attention Network For VideoQA | JIAYIN CAI et. al. | To tackle these problems, we propose a novel VideoQA framework which progressively refines the representations of videos and questions from fine to coarse grain in a sequence-sensitive manner. | CS.ijcai | 2020-07-21 |
| 260 | Transformers As Soft Reasoners Over Language | PETER CLARK et. al. | This paper investigates a modern approach to this problem where the facts and rules are provided as natural language sentences, thus bypassing a formal representation. | CS.ijcai | 2020-07-21 |
| 261 | AILA: A Question Answering System In The Legal Domain | WEIYI HUANG et. al. | In this paper, we develop an Artificial Intelligence Law Assistant (AILA) for question answering in the domain of Chinese laws. | CS.ijcai | 2020-07-21 |
| 262 | Overcoming Language Priors With Self-supervised Learning For Visual Question Answering | XI ZHU et. al. | In this paper, we introduce a self-supervised learning framework to solve this problem. Concretely, we first automatically generate labeled data to balance the biased data, and then propose a self-supervised auxiliary task to utilize the balanced data to assist the VQA model to overcome language priors. | CS.ijcai | 2020-07-21 |
| 263 | Asking Effective And Diverse Questions: A Machine Reading Comprehension Based Framework For Joint Entity-Relation Extraction | TIANYANG ZHAO et. al. | In this paper, we improve the existing MRC-based entity-relation extraction model through diverse question answering. | CS.ijcai | 2020-07-21 |
| 264 | Generating Reasonable Legal Text Through The Combination Of Language Modeling And Question Answering | WEIJING HUANG et. al. | To generate reasonable legal documents, we propose a novel method CoLMQA, which (1) combines Language Modeling and Question Answering, (2) generates text with slots by Language Modeling, and (3) fills the slots by our proposed Question Answering method named Transformer-based Key-Value Memory Networks. | CS.ijcai | 2020-07-21 |
| 265 | LogiQA: A Challenge Dataset For Machine Reading Comprehension With Logical Reasoning | JIAN LIU et. al. | We build a comprehensive dataset, named LogiQA, which is sourced from expert-written questions for testing human Logical reasoning. | CS.ijcai | 2020-07-21 |
| 266 | Sybil-proof Answer Querying Mechanism | YAO ZHANG et. al. | We study a question answering problem on a social network, where a requester is seeking an answer from the agents on the network. | CS.ijcai | 2020-07-21 |
| 267 | Distributed Memory Based Self-Supervised Differentiable Neural Computer | TAEWON PARK et. al. | To address those issues, we propose a novel distributed memory-based self-supervised DNC architecture for enhanced memory augmented neural network performance. | CS.arxiv | 2020-07-21 |
| 268 | Frustratingly Hard Evidence Retrieval For QA Over Books | XIANGYANG MOU et. al. | We formulate BookQA as an open-domain QA task given its similar dependency on evidence retrieval. | CS.arxiv | 2020-07-20 |
| 269 | Multimodal Dialogue State Tracking By QA Approach With Data Augmentation | XIANGYANG MOU et. al. | This paper interprets the AVSD task from an open-domain Question Answering (QA) point of view and proposes a multimodal open-domain QA system to deal with the problem. | CS.arxiv | 2020-07-20 |
| 270 | AWS CORD-19 Search: A Neural Search Engine For COVID-19 Literature | PARMINDER BHATIA et. al. | To support this cause we present AWS CORD-19 Search (ACS), a public, COVID-19 specific, neural search engine that is powered by several machine learning systems to support natural language based searches. | CS.arxiv | 2020-07-17 |
| 271 | XAlgo: Explaining The Internal States Of Algorithms Via Question Answering | JUAN REBANAL et. al. | We contribute a formal model that first classifies the type of question based on a taxonomy, and generates an answer based on a set of rules that extract information from representations of an algorithm’s internal states, e.g., the pseudocode. | CS.arxiv | 2020-07-14 |
| 272 | Template-Based Question Answering Over Linked Geospatial Data | DHARMEN PUNJANI et. al. | In this paper, we go beyond these approaches to offer a question-answering engine for natural language questions on top of linked geospatial data sources. | CS.arxiv | 2020-07-14 |
| 273 | Using Holographically Compressed Embeddings In Question Answering | SALVADOR E. BARBOSA | This research employs holographic compression of pre-trained embeddings, to represent a token, its part-of-speech, and named entity type, in the same dimension as representing only the token. | CS.arxiv | 2020-07-14 |
| 274 | Probing Emergent Semantics In Predictive Agents Via Question Answering | ABHISHEK DAS et. al. | We propose question-answering as a general paradigm to decode and understand the representations that such agents develop, applying our method to two recent approaches to predictive modelling – action-conditional CPC (Guo et al., 2018) and SimCore (Gregor et al., 2019). | CS.icml | 2020-07-11 |
| 275 | Neuro-Symbolic Visual Reasoning: Disentangling "Visual" From "Reasoning" | SAEED AMIZADEH et. al. | To address this, we propose (1) a framework to isolate and evaluate the reasoning aspect of VQA separately from its perception, and (2) a novel top-down calibration technique that allows the model to answer reasoning questions even with imperfect perception. | CS.icml | 2020-07-11 |
| 276 | Multigrid Neural Memory | TRI HUYNH et. al. | We introduce a radical new approach to endowing neural networks with access to long-term and large-scale memory. | CS.icml | 2020-07-11 |
| 277 | The Effect Of Natural Distribution Shift On Question Answering Models | JOHN MILLER et. al. | Taken together, our results confirmthe surprising resilience of the holdout methodand emphasize the need to move towards evalua-tion metrics that incorporate robustness to naturaldistribution shifts. | CS.icml | 2020-07-11 |
| 278 | Description Based Text Classification With Reinforcement Learning | WEI WU et. al. | Inspired by the current trend of formalizing NLP problems as question answering tasks, we propose a new framework for text classification, in which each category label is associated with a category description. | CS.icml | 2020-07-11 |
| 279 | Applying Recent Advances In Visual Question Answering To Record Linkage | MARKO SMILEVSKI | This field has not been explored in research and we propose two solutions based on Deep Learning architectures that are inspired by recent work in Visual Question Answering. | CS.arxiv | 2020-07-11 |
| 280 | Closed Loop Neural-Symbolic Learning Via Integrating Neural Perception, Grammar Parsing, And Symbolic Reasoning | QING LI et. al. | In this paper, we address these issues and close the loop of neural-symbolic learning by (1) introducing the grammar model as a symbolic prior to bridge neural perception and symbolic reasoning, and (2) proposing a novel back-search algorithm which mimics the top-down human-like learning procedure to propagate the error through the symbolic reasoning module efficiently. | CS.icml | 2020-07-11 |
| 281 | Retrieval Augmented Language Model Pre-Training | KELVIN GUU et. al. | To capture knowledge in a more modular and interpretable way, we augment language model pre-training with a latent knowledge retriever, which allows the model to retrieve and attend over documents from a large corpus such as Wikipedia, used during pre-training, fine-tuning and inference. | CS.icml | 2020-07-11 |
| 282 | Self-Attentive Associative Memory | HUNG LE et. al. | In this paper, we propose to separate the storage of individual experiences (item memory) and their occurring relationships (relational memory). | CS.icml | 2020-07-11 |
| 283 | What Can We Learn From Almost A Decade Of Food Tweets | UGA SPROĢIS et. al. | We present the Latvian Twitter Eater Corpus – a set of tweets in the narrow domain related to food, drinks, eating and drinking. | CS.arxiv | 2020-07-10 |
| 284 | Image Captioning With Compositional Neural Module Networks | JUNJIAO TIAN et. al. | Inspired by the idea of the compositional neural module networks in the visual question answering task, we introduce a hierarchical framework for image captioning that explores both compositionality and sequentiality of natural language. | CS.arxiv | 2020-07-10 |
| 285 | Not Your Grandfathers Test Set: Reducing Labeling Effort For Testing | BEGUM TASKAZAN et. al. | This paper proposes a simple but effective technique that drastically reduces the effort needed to construct and maintain a high-quality test set (reducing labeling effort by 80-100% across a range of practical scenarios). | CS.arxiv | 2020-07-10 |
| 286 | Advances Of Transformer-Based Models For News Headline Generation | ALEXEY BUKHTIYAROV et. al. | In this paper, we fine-tune two pretrained Transformer-based models (mBART and BertSumAbs) for that task and achieve new state-of-the-art results on the RIA and Lenta datasets of Russian news. | CS.arxiv | 2020-07-09 |
| 287 | Less Is More: Rejecting Unreliable Reviews For Product Question Answering | SHIWEI ZHANG et. al. | In this paper, we focus on the issue of answerability and answer reliability for PQA using reviews. | CS.arxiv | 2020-07-08 |
| 288 | IQ-VQA: Intelligent Visual Question Answering | VATSAL GOEL et. al. | To this end, we propose a model-independent cyclic framework which increases consistency and robustness of any VQA architecture. As a baseline for future works on consistency, we provide a new human annotated VQA-Implications dataset. | CS.arxiv | 2020-07-08 |
| 289 | KQA Pro: A Large Diagnostic Dataset For Complex Question Answering Over Knowledge Base | JIAXIN SHI et. al. | To this end, we introduce KQA Pro, a large-scale dataset for Complex KBQA. | CS.arxiv | 2020-07-07 |
| 290 | What Gives The Answer Away? Question Answering Bias Analysis On Video QA Datasets | JIANING YANG et. al. | In this paper, we analyze QA biases in popular video question answering datasets and discover pretrained language models can answer 37-48% questions correctly without using any multimodal context information, far exceeding the 20% random guess baseline for 5-choose-1 multiple-choice questions. | CS.arxiv | 2020-07-07 |
| 291 | Towards Personalized Privacy-Preserving Incentive For Truth Discovery In Crowdsourced Binary-Choice Question Answering | P. SUN ET AL. | In this paper, we propose a contract-based personalized privacy-preserving incentive mechanism for truth discovery in crowdsourced question answering systems, named PINTION, which provides personalized payments for workers with different privacy demands as a compensation for privacy cost, while ensuring accurate truth discovery. | CS.infocom | 2020-07-06 |
| 292 | Auto-captions On GIF: A Large-scale Video-sentence Dataset For Vision-language Pre-training | YINGWEI PAN et. al. | In this work, we present Auto-captions on GIF, which is a new large-scale pre-training dataset for generic video understanding. | CS.arxiv | 2020-07-05 |
| 293 | Text Data Augmentation: Towards Better Detection Of Spear-phishing Emails | MEHDI REGINA et. al. | Motivated by a business application of Business Email Compromise (BEC) detection, we propose a corpus and task agnostic text augmentation framework combining different methods, utilizing BERT language model, multi-step back-translation and heuristics. | CS.arxiv | 2020-07-04 |
| 294 | Modality Shifting Attention Network For Multi-modal Video Question Answering | JUNYEONG KIM et. al. | This paper considers a network referred to as Modality Shifting Attention Network (MSAN) for Multimodal Video Question Answering (MVQA) task. | CS.arxiv | 2020-07-04 |
| 295 | Visual Question Answering As A Multi-Task Problem | AMELIA ELIZABETH POLLARD et. al. | In this paper, we present the hypothesis that Visual Question Answering should be viewed as a multi-task problem, and provide evidence to support this hypothesis. | CS.arxiv | 2020-07-03 |
| 296 | El Departamento De Nosotros: How Machine Translated Corpora Affects Language Models In MRC Tasks | MARIA KHVALCHIK et. al. | In this work, we study the caveats of applying directly translated corpora for fine-tuning LMs for downstream natural language processing tasks and demonstrate that careful curation along with post-processing lead to improved performance and overall LMs robustness. | CS.arxiv | 2020-07-03 |
| 297 | IIE-NLP-NUT At SemEval-2020 Task 4: Guiding PLM With Prompt Template Reconstruction Strategy For ComVE | LUXI XING et. al. | This paper introduces our systems for the first two subtasks of SemEval Task4: Commonsense Validation and Explanation. | CS.arxiv | 2020-07-02 |
| 298 | The Impact Of Explanations On AI Competency Prediction In VQA | KAMRAN ALIPOUR et. al. | In this paper, we evaluate the impact of explanations on the user’s mental model of AI agent competency within the task of visual question answering (VQA). | CS.arxiv | 2020-07-02 |
| 299 | Improving Event Detection Using Contextual Word And Sentence Embeddings | MARIANO MAISONNAVE et. al. | The main contribution of this paper is the design, implementation and evaluation of a recurrent neural network model for ED that combines several features. | CS.arxiv | 2020-07-02 |
| 300 | Scene Graph Reasoning For Visual Question Answering | MARCEL HILDEBRANDT et. al. | We propose a novel method that approaches the task by performing context-driven, sequential reasoning based on the objects and their semantic and spatial relationships present in the scene. | CS.arxiv | 2020-07-02 |
| 301 | Leveraging Passage Retrieval With Generative Models For Open Domain Question Answering | GAUTIER IZACARD et. al. | In this paper, we investigate how much these models can benefit from retrieving text passages, potentially containing evidence. | CS.arxiv | 2020-07-02 |
| 302 | Project PIAF: Building A Native French Question-Answering Dataset | RACHEL KERARON et. al. | Motivated by the lack of data for non-English languages, in particular for the evaluation of downstream tasks such as Question Answering, we present a participatory effort to collect a native French Question Answering Dataset. | CS.arxiv | 2020-07-02 |
| 303 | Latent Compositional Representations Improve Systematic Generalization In Grounded Question Answering | BEN BOGIN et. al. | In this work, we propose a model that computes a representation and denotation for all question spans in a bottom-up, compositional manner using a CKY-style parser. | CS.arxiv | 2020-07-01 |
| 304 | Transferability Of Natural Language Inference To Biomedical Question Answering | MINBYUL JEONG et. al. | In this paper, we focus on applying BioBERT to transfer the knowledge of natural language inference (NLI) to biomedical QA. | CS.arxiv | 2020-07-01 |
| 305 | DocVQA: A Dataset For VQA On Document Images | MINESH MATHEW et. al. | We present a new dataset for Visual Question Answering on document images called DocVQA. | CS.arxiv | 2020-07-01 |
| 306 | Facts As Experts: Adaptable And Interpretable Neural Memory Over Symbolic Knowledge | PAT VERGA et. al. | To address these problems, we develop a neural language model that includes an explicit interface between symbolically interpretable factual information and subsymbolic neural knowledge. | CS.arxiv | 2020-07-01 |
| 307 | Relevance-guided Supervision For OpenQA With ColBERT | OMAR KHATTAB et. al. | We propose a weak supervision strategy that iteratively uses ColBERT to create its own training data. | CS.arxiv | 2020-07-01 |
| 308 | COVID-19 Literature Knowledge Graph Construction And Drug Repurposing Report Generation | QINGYUN WANG et. al. | We have developed a novel and comprehensive knowledge discovery framework, \textbf{COVID-KG} to extract fine-grained multimedia knowledge elements (entities, relations and events) from scientific literature. | CS.arxiv | 2020-07-01 |
| 309 | Correction Of Faulty Background Knowledge Based On Condition Aware And Revise Transformer For Question Answering | XINYAN ZHAO et. al. | To alleviate the effect of defective condition values, this paper proposes condition aware and revise Transformer (CAR-Transformer). | CS.arxiv | 2020-06-30 |
| 310 | Ontology-guided Semantic Composition For Zero-Shot Learning | JIAOYAN CHEN et. al. | Ontology-guided Semantic Composition For Zero-Shot Learning | CS.arxiv | 2020-06-30 |
| 311 | Answering Questions On COVID-19 In Real-Time | JINHYUK LEE et. al. | In this work, we outline our effort to contribute to shrinking this knowledge vacuum by creating covidAsk, a question answering (QA) system that combines biomedical text mining and QA techniques to provide answers to questions in real-time. | CS.arxiv | 2020-06-29 |
| 312 | Improving VQA And Its Explanations \\ By Comparing Competing Explanations | JIALIN WU et. al. | To address this issue, we present a novel framework that uses explanations for competing answers to help VQA systems select the correct answer. | CS.arxiv | 2020-06-28 |
| 313 | Graph Optimal Transport For Cross-Domain Alignment | LIQUN CHEN et. al. | We propose Graph Optimal Transport (GOT), a principled framework that germinates from recent advances in Optimal Transport (OT). | CS.arxiv | 2020-06-25 |
| 314 | Self-Segregating And Coordinated-Segregating Transformer For Focused Deep Multi-Modular Network For Visual Question Answering | CHIRANJIB SUR | We defined two strategies: Self-Segregating Transformer (SST) and Coordinated-Segregating Transformer (CST) and used it to solve visual question answering application. | CS.arxiv | 2020-06-25 |
| 315 | Does The Whole Exceed Its Parts? The Effect Of AI Explanations On Complementary Team Performance | GAGAN BANSAL et. al. | Can we develop explanatory approaches that help humans decide whether and when to trust AI input? | CS.arxiv | 2020-06-25 |
| 316 | NLPContributions: An Annotation Scheme For Machine Reading Of Scholarly Contributions In Natural Language Processing Literature | JENNIFER D’SOUZA et. al. | In this article, we describe the outcomes of this pilot annotation phase. | CS.arxiv | 2020-06-23 |
| 317 | ReCO: A Large Scale Chinese Reading Comprehension Dataset On Opinion | BINGNINGWANG et. al. | This paper presents the ReCO, a human-curated ChineseReading Comprehension dataset on Opinion. | CS.arxiv | 2020-06-22 |
| 318 | Match$^2$: A Matching Over Matching Model For Similar Question Identification | ZIZHEN WANG et. al. | In this work, we propose a two-side usage, which leverages the answer as a bridge of the two questions. | CS.arxiv | 2020-06-21 |
| 319 | MATINF: A Jointly Labeled Large-Scale Dataset For Classification, Question Answering And Summarization | CANWEN XU et. al. | We propose MATINF, the first jointly labeled large-scale dataset for classification, question answering and summarization. | CS.acl | 2020-06-20 |
| 320 | MLQA: Evaluating Cross-lingual Extractive Question Answering | PATRICK LEWIS et. al. | We present MLQA, a multi-way aligned extractive QA evaluation benchmark intended to spur research in this area. | CS.acl | 2020-06-20 |
| 321 | ClarQ: A Large-scale And Diverse Dataset For Clarification Question Generation | VAIBHAV KUMAR et. al. | In order to overcome these limitations, we devise a novel bootstrapping framework (based on self-supervision) that assists in the creation of a diverse, large-scale dataset of clarification questions based on post-comment tuples extracted from stackexchange. | CS.acl | 2020-06-20 |
| 322 | GLUECoS: An Evaluation Benchmark For Code-Switched NLP | SIMRAN KHANUJA et. al. | We present an evaluation benchmark, GLUECoS, for code-switched languages, that spans several NLP tasks in English-Hindi and English-Spanish. | CS.acl | 2020-06-20 |
| 323 | Transformers To Learn Hierarchical Contexts In Multiparty Dialogue For Span-based Question Answering | CHANGMAO LI et. al. | We introduce a novel approach to transformers that learns hierarchical representations in multiparty dialogue. | CS.acl | 2020-06-20 |
| 324 | QuASE: Question-Answer Driven Sentence Encoding | HANGFENG HE et. al. | This paper studies a natural question: Can we get supervision from QA data for other tasks (typically, non-QA ones)? | CS.acl | 2020-06-20 |
| 325 | Probabilistic Assumptions Matter: Improved Models For Distantly-Supervised Document-Level Question Answering | HAO CHENG et. al. | We address the problem of extractive question answering using document-level distant super-vision, pairing questions and relevant documents with answer strings. | CS.acl | 2020-06-20 |
| 326 | Selective Question Answering Under Domain Shift | AMITA KAMATH et. al. | In this work, we propose the setting of selective question answering under domain shift, in which a QA model is tested on a mixture of in-domain and out-of-domain data, and must answer (i.e., not abstain on) as many questions as possible while maintaining high accuracy. | CS.acl | 2020-06-20 |
| 327 | Multimodal Neural Graph Memory Networks For Visual Question Answering | MAHMOUD KHADEMI | We introduce a new neural network architecture, Multimodal Neural Graph Memory Networks (MN-GMN), for visual question answering. | CS.acl | 2020-06-20 |
| 328 | Span Selection Pre-training For Question Answering | MICHAEL GLASS et. al. | In this paper we introduce a new pre-training task inspired by reading comprehension to better align the pre-training from memorization to understanding. | CS.acl | 2020-06-20 |
| 329 | Improving Multi-hop Question Answering Over Knowledge Graphs Using Knowledge Base Embeddings | APOORV SAXENA et. al. | We fill this gap in this paper and propose EmbedKGQA. EmbedKGQA is particularly effective in performing multi-hop KGQA over sparse KGs. | CS.acl | 2020-06-20 |
| 330 | On The Cross-lingual Transferability Of Monolingual Representations | MIKEL ARTETXE et. al. | More concretely, we first train a transformer-based masked language model on one language, and transfer it to a new language by learning a new embedding matrix with the same masked language modeling objective, freezing parameters of all other layers. | CS.acl | 2020-06-20 |
| 331 | Dense-Caption Matching And Frame-Selection Gating For Temporal Localization In VideoQA | HYOUNGHUN KIM et. al. | In this paper, we propose a video question answering model which effectively integrates multi-modal input sources and finds the temporally relevant information to answer questions. | CS.acl | 2020-06-20 |
| 332 | TVQA+: Spatio-Temporal Grounding For Video Question Answering | JIE LEI et. al. | We present the task of Spatio-Temporal Video Question Answering, which requires intelligent systems to simultaneously retrieve relevant moments and detect referenced visual concepts (people and objects) to answer natural language questions about videos. | CS.acl | 2020-06-20 |
| 333 | Temporal Common Sense Acquisition With Minimal Supervision | BEN ZHOU et. al. | This work proposes a novel sequence modeling approach that exploits explicit and implicit mentions of temporal common sense, extracted from a large corpus, to build TacoLM, a temporal common sense language model. | CS.acl | 2020-06-20 |
| 334 | Logic-Guided Data Augmentation And Regularization For Consistent Question Answering | AKARI ASAI et. al. | This paper addresses the problem of improving the accuracy and consistency of responses to comparison questions by integrating logic rules and neural models. | CS.acl | 2020-06-20 |
| 335 | Learning To Identify Follow-Up Questions In Conversational Question Answering | SOUVIK KUNDU et. al. | In this paper, we introduce a new follow-up question identification task. | CS.acl | 2020-06-20 |
| 336 | DeFormer: Decomposing Pre-trained Transformers For Faster Question Answering | QINGQING CAO et. al. | We introduce DeFormer, a decomposed transformer, which substitutes the full self-attention with question-wide and passage-wide self-attentions in the lower layers. | CS.acl | 2020-06-20 |
| 337 | Calibrating Structured Output Predictors For Natural Language Processing | ABHYUDAY JAGANNATHA et. al. | In this study, we propose a general calibration scheme for output entities of interest in neural network based structured prediction models. | CS.acl | 2020-06-20 |
| 338 | TaPas: Weakly Supervised Table Parsing Via Pre-training | JONATHAN HERZIG et. al. | In this paper, we present TaPas, an approach to question answering over tables without generating logical forms. | CS.acl | 2020-06-20 |
| 339 | Controlled Crowdsourcing For High-Quality QA-SRL Annotation | PAUL ROIT et. al. | In this paper, we present an improved crowdsourcing protocol for complex semantic annotation, involving worker selection and training, and a data consolidation phase. | CS.acl | 2020-06-20 |
| 340 | Neuro-Symbolic Visual Reasoning: Disentangling Visual From Reasoning | SAEED AMIZADEH et. al. | To address this, we propose (1) a framework to isolate and evaluate the reasoning aspect of VQA separately from its perception, and (2) a novel top-down calibration technique that allows the model to answer reasoning questions even with imperfect perception. | CS.arxiv | 2020-06-20 |
| 341 | Aligned Dual Channel Graph Convolutional Network For Visual Question Answering | QINGBAO HUANG et. al. | To simultaneously capture the relations between objects in an image and the syntactic dependency relations between words in a question, we propose a novel dual channel graph convolutional network (DC-GCN) for better combining visual and textual advantages. | CS.acl | 2020-06-20 |
| 342 | Memory Transformer | MIKHAIL S. BURTSEV et. al. | In this work, we propose and study two extensions of the Transformer baseline (1) by adding memory tokens to store non-local representations, and (2) creating memory bottleneck for the global information. | CS.arxiv | 2020-06-20 |
| 343 | IQA: Interactive Query Construction In Semantic Question Answering Systems | HAMID ZAFAR et. al. | In this article, we aim to empower users in guiding SQA systems towards the intended semantic queries through interaction. | CS.arxiv | 2020-06-20 |
| 344 | Fluent Response Generation For Conversational Question Answering | ASHUTOSH BAHETI et. al. | In this work, we propose a method for situating QA responses within a SEQ2SEQ NLG approach to generate fluent grammatical answer responses while maintaining correctness. | CS.acl | 2020-06-20 |
| 345 | On The Importance Of Diversity In Question Generation For QA | MD ARAFAT SULTAN et. al. | In this paper we ask: Is textual diversity in QG beneficial for downstream QA? | CS.acl | 2020-06-20 |
| 346 | A Methodology For Creating Question Answering Corpora Using Inverse Data Annotation | JAN DERIU et. al. | In this paper, we introduce a novel methodology to efficiently construct a corpus for question answering over structured data. | CS.acl | 2020-06-20 |
| 347 | Span-based Localizing Network For Natural Language Video Localization | HAO ZHANG et. al. | In this work, we address NLVL task with a span-based QA approach by treating the input video as text passage. | CS.acl | 2020-06-20 |
| 348 | What Question Answering Can Learn From Trivia Nerds | JORDAN BOYD-GRABER et. al. | We argue that creating a QA dataset-and the ubiquitous leaderboard that goes with it-closely resembles running a trivia tournament: you write questions, have agents (either humans or machines) answer the questions, and declare a winner. | CS.acl | 2020-06-20 |
| 349 | Contextualized Sparse Representations For Real-Time Open-Domain Question Answering | JINHYUK LEE et. al. | In this paper, we aim to improve the quality of each phrase embedding by augmenting it with a contextualized sparse representation (Sparc). | CS.acl | 2020-06-20 |
| 350 | FEQA: A Question Answering Evaluation Framework For Faithfulness Assessment In Abstractive Summarization | ESIN DURMUS et. al. | We tackle the problem of evaluating faithfulness of a generated summary given its source document. | CS.acl | 2020-06-20 |
| 351 | Recurrent Chunking Mechanisms For Long-Text Machine Reading Comprehension | HONGYU GONG et. al. | In this paper, we study machine reading comprehension (MRC) on long texts: where a model takes as inputs a lengthy document and a query, extracts a text span from the document as an answer. | CS.acl | 2020-06-20 |
| 352 | DoQA – Accessing Domain-Specific FAQs Via Conversational QA | JON ANDER CAMPOS et. al. | The goal of this work is to build conversational Question Answering (QA) interfaces for the large body of domain-specific information available in FAQ sites. | CS.acl | 2020-06-20 |
| 353 | The Cascade Transformer: An Application For Efficient Answer Sentence Selection | LUCA SOLDAINI et. al. | In this paper, we introduce the Cascade Transformer, a simple yet effective technique to adapt transformer-based models into a cascade of rankers. | CS.acl | 2020-06-20 |
| 354 | KLEJ: Comprehensive Benchmark For Polish Language Understanding | PIOTR RYBAK et. al. | To alleviate this issue, we introduce a comprehensive multi-task benchmark for the Polish language understanding, accompanied by an online leaderboard. | CS.acl | 2020-06-20 |
| 355 | Clinical Reading Comprehension: A Thorough Analysis Of The EmrQA Dataset | XIANG YUE et. al. | In this paper, we provide an in-depth analysis of this dataset and the clinical reading comprehension (CliniRC) task. | CS.acl | 2020-06-20 |
| 356 | Towards Conversational Recommendation Over Multi-Type Dialogs | ZEMING LIU et. al. | We focus on the study of conversational recommendation in the context of multi-type dialogs, where the bots can proactively and naturally lead a conversation from a non-recommendation dialog (e.g., QA) to a recommendation dialog, taking into account user’s interests and feedback. | CS.acl | 2020-06-20 |
| 357 | Generating Diverse And Consistent QA Pairs From Contexts With Information-Maximizing Hierarchical Conditional VAEs | DONG BOK LEE et. al. | In this work, we propose a hierarchical conditional variational autoencoder (HCVAE) for generating QA pairs given unstructured texts as contexts, while maximizing the mutual information between generated QA pairs to ensure their consistency. | CS.acl | 2020-06-20 |
| 358 | Cross-Modality Relevance For Reasoning On Language And Vision | CHEN ZHENG et. al. | This work deals with the challenge of learning and reasoning over language and vision data for the related downstream tasks such as visual question answering (VQA) and natural language for visual reasoning (NLVR). | CS.acl | 2020-06-20 |
| 359 | A Self-Training Method For Machine Reading Comprehension With Soft Evidence Extraction | YILIN NIU et. al. | To address this problem, we present a Self-Training method (STM), which supervises the evidence extractor with auto-generated evidence labels in an iterative process. | CS.acl | 2020-06-20 |
| 360 | Unsupervised Alignment-based Iterative Evidence Retrieval For Multi-hop Question Answering | VIKAS YADAV et. al. | We introduce a simple, fast, and unsupervised iterative evidence retrieval method, which relies on three ideas: (a) an unsupervised alignment approach to soft-align questions and answers with justification sentences using only GloVe embeddings, (b) an iterative process that reformulates queries focusing on terms that are not covered by existing justifications, which (c) stops when the terms in the given question and candidate answers are covered by the retrieved justifications. | CS.acl | 2020-06-20 |
| 361 | Harvesting And Refining Question-Answer Pairs For Unsupervised QA | ZHONGLI LI et. al. | In this work, we introduce two approaches to improve unsupervised QA. | CS.acl | 2020-06-20 |
| 362 | The TechQA Dataset | VITTORIO CASTELLI et. al. | We introduce TECHQA, a domain-adaptation question answering dataset for the technical support domain. | CS.acl | 2020-06-20 |
| 363 | Template-Based Question Generation From Retrieved Sentences For Improved Unsupervised Question Answering | ALEXANDER FABBRI et. al. | We propose an unsupervised approach to training QA models with generated pseudo-training data. | CS.acl | 2020-06-20 |
| 364 | MobileBERT: A Compact Task-Agnostic BERT For Resource-Limited Devices | ZHIQING SUN et. al. | In this paper, we propose MobileBERT for compressing and accelerating the popular BERT model. | CS.acl | 2020-06-20 |
| 365 | CorefQA: Coreference Resolution As Query-based Span Prediction | WEI WU et. al. | In this paper, we present CorefQA, an accurate and extensible approach for the coreference resolution task. | CS.acl | 2020-06-20 |
| 366 | Evaluating And Enhancing The Robustness Of Neural Network-based Dependency Parsing Models With Adversarial Examples | XIAOQING ZHENG et. al. | In this study, we show that adversarial examples also exist in dependency parsing: we propose two approaches to study where and how parsers make mistakes by searching over perturbations to existing texts at sentence and phrase levels, and design algorithms to construct such examples in both of the black-box and white-box settings. | CS.acl | 2020-06-20 |
| 367 | PLATO: Pre-trained Dialogue Generation Model With Discrete Latent Variable | SIQI BAO et. al. | Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including chit-chat, knowledge grounded dialogues, and conversational question answering. | CS.acl | 2020-06-20 |
| 368 | BART: Denoising Sequence-to-Sequence Pre-training For Natural Language Generation, Translation, And Comprehension | MIKE LEWIS et. al. | We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. | CS.acl | 2020-06-20 |
| 369 | Interactive Machine Comprehension With Information Seeking Agents | XINGDI YUAN et. al. | In this paper, we propose a simple method that reframes existing MRC datasets as interactive, partially observable environments. | CS.acl | 2020-06-20 |
| 370 | RikiNet: Reading Wikipedia Pages For Natural Question Answering | DAYIHENG LIU et. al. | In this paper, we introduce a new model, called RikiNet, which reads Wikipedia pages for natural question answering. | CS.acl | 2020-06-20 |
| 371 | Incorporating External Knowledge Through Pre-training For Natural Language To Code Generation | FRANK F. XU et. al. | Motivated by the intuition that developers usually retrieve resources on the web when writing code, we explore the effectiveness of incorporating two varieties of external knowledge into NL-to-code generation: automatically mined NL-code pairs from the online programming QA forum StackOverflow and programming language API documentation. | CS.acl | 2020-06-20 |
| 372 | Multi-source Meta Transfer For Low Resource Multiple-Choice Question Answering | MING YAN et. al. | To address this challenge, we propose a multi-source meta transfer (MMT) for low-resource MCQA. | CS.acl | 2020-06-20 |
| 373 | A Negative Case Analysis Of Visual Grounding Methods For VQA | ROBIK SHRESTHA et. al. | However, we show that the performance improvements are not a result of improved visual grounding, but a regularization effect which prevents over-fitting to linguistic priors. | CS.acl | 2020-06-20 |
| 374 | A Qualitative Evaluation Of Language Models On Automatic Question-Answering For COVID-19 | DAVID ONIANI et. al. | In this paper, we propose to apply a language model for automatically answering questions related to COVID-19 and qualitatively evaluate the generated responses. | CS.arxiv | 2020-06-19 |
| 375 | Results Of The Seventh Edition Of The BioASQ Challenge | ANASTASIOS NENTIDIS et. al. | The results of the seventh edition of the BioASQ challenge are presented in this paper. | CS.arxiv | 2020-06-16 |
| 376 | CO-Search: COVID-19 Information Retrieval With Semantic Search, Question Answering, And Abstractive Summarization | ANDRE ESTEVA et. al. | Here we present CO-Search, a retriever-ranker semantic search engine designed to handle complex queries over the COVID-19 literature, potentially aiding overburdened health workers in finding scientific answers during a time of crisis. | CS.arxiv | 2020-06-16 |
| 377 | ORD: Object Relationship Discovery For Visual Dialogue Generation | ZIWEI WANG et. al. | In this paper, we propose an object relationship discovery (ORD) framework to preserve the object interactions for visual dialogue generation. | CS.arxiv | 2020-06-15 |
| 378 | Sparse And Continuous Attention Mechanisms | ANDRÉ F. T. MARTINS et. al. | Sparse And Continuous Attention Mechanisms | CS.arxiv | 2020-06-12 |
| 379 | Video Understanding As Machine Translation | BRUNO KORBAR et. al. | In this work we remove the need for negative sampling by taking a generative modeling approach that poses the objective as a translation problem between modalities. | CS.arxiv | 2020-06-12 |
| 380 | Large-Scale Adversarial Training For Vision-and-Language Representation Learning | ZHE GAN et. al. | We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. | CS.arxiv | 2020-06-11 |
| 381 | Exploring Weaknesses Of VQA Models Through Attribution Driven Insights | SHAUNAK HALBE | Recent research effectively applies these VQA models for answering visual questions for the blind. | CS.arxiv | 2020-06-11 |
| 382 | ClarQ: A Large-scale And Diverse Dataset For Clarification Question Generation | VAIBHAV KUMAR et. al. | In order to overcome these limitations, we devise a novel bootstrapping framework (based on self-supervision) that assists in the creation of a diverse, large-scale dataset of clarification questions based on post-comment tuples extracted from stackexchange. We release this dataset in order to foster research into the field of clarification question generation with the larger goal of enhancing dialog and question answering systems. | CS.arxiv | 2020-06-10 |
| 383 | Consolidating Commonsense Knowledge | FILIP ILIEVSKI et. al. | In this paper, we list representative sources and their properties. | CS.arxiv | 2020-06-10 |
| 384 | Map3D: Registration Based Multi-Object Tracking On 3D Serial Whole Slide Images | RUINING DENG et. al. | In this paper, we propose a novel Multi-Object Association for Pathology in 3D (Map3D) method for automatically identifying and associating large-scale cross-sections of 3D objects from routine serial sectioning and WSI. | CS.arxiv | 2020-06-10 |
| 385 | Estimating Semantic Structure For The VQA Answer Space | CORENTIN KERVADEC et. al. | We address this issue by proposing (1) two measures of proximity between VQA classes, and (2) a corresponding loss which takes into account the estimated proximity. | CS.arxiv | 2020-06-10 |
| 386 | Knowledge-Aided Open-Domain Question Answering | MANTONG ZHOU et. al. | In this work, we propose a knowledge-aided open-domain QA (KAQA) method which targets at improving relevant document retrieval and candidate answer reranking by considering the relationship between a question and the documents (termed as question-document graph), and the relationship between candidate documents (termed as document-document graph). | CS.arxiv | 2020-06-09 |
| 387 | Roses Are Red, Violets Are Blue… But Should Vqa Expect Them To? | CORENTIN KERVADEC et. al. | In this work, we design a new benchmark based on a fine-grained reorganization of the GQA dataset [1], which allows to precisely answer these questions. | CS.arxiv | 2020-06-09 |
| 388 | Foreshadowing The Benefits Of Incidental Supervision | HANGFENG HE et. al. | To quantify the benefits of various incidental supervision signals, we propose a unified PAC-Bayesian Informativeness measure (PABI), characterizing the reduction in uncertainty that incidental supervision signals provide. | CS.arxiv | 2020-06-09 |
| 389 | Hypergraph Attention Networks For Multimodal Learning | EUN-SOL KIM et. al. | To resolve this problem, we propose Hypergraph Attention Networks (HANs), which define a common semantic space among the modalities with symbolic graphs and extract a joint representation of the modalities based on a co-attention map constructed in the semantic space. | CS.cvpr | 2020-06-08 |
| 390 | On The General Value Of Evidence, And Bilingual Scene-Text Visual Question Answering | XINYU WANG et. al. | We present a dataset that takes a step towards addressing this problem in that it contains questions expressed in two languages, and an evaluation process that co-opts a well understood image-based metric to reflect the method’s ability to reason. | CS.cvpr | 2020-06-08 |
| 391 | TA-Student VQA: Multi-Agents Training By Self-Questioning | PEIXI XIONG et. al. | We introduce our self-questioning model with multi-agent training: TA-student VQA. | CS.cvpr | 2020-06-08 |
| 392 | Assessing Image Quality Issues For Real-World Problems | TAI-YIN CHIU et. al. | We introduce a new large-scale dataset that links the assessment of image quality issues to two practical vision tasks: image captioning and visual question answering. | CS.cvpr | 2020-06-08 |
| 393 | Normalized And Geometry-Aware Self-Attention Network For Image Captioning | LONGTENG GUO et. al. | In this paper, we improve SA from two aspects to promote the performance of image captioning. | CS.cvpr | 2020-06-08 |
| 394 | In Defense Of Grid Features For Visual Question Answering | HUAIZU JIANG et. al. | In this paper, we revisit grid features for VQA, and find they can work surprisingly well — running more than an order of magnitude faster with the same accuracy (e.g. if pre-trained in a similar fashion). | CS.cvpr | 2020-06-08 |
| 395 | ActBERT: Learning Global-Local Video-Text Representations | LINCHAO ZHU et. al. | In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data. | CS.cvpr | 2020-06-08 |
| 396 | Towards Causal VQA: Revealing And Reducing Spurious Correlations By Invariant And Covariant Semantic Editing | VEDIKA AGARWAL et. al. | In this paper, we propose a novel way to analyze and measure the robustness of the state of the art models w.r.t semantic visual variations as well as propose ways to make models more robust against spurious correlations. | CS.cvpr | 2020-06-08 |
| 397 | Multi-Modal Graph Neural Network For Joint Reasoning On Vision And Scene Text | DIFEI GAO et. al. | Following this idea, we propose a novel VQA approach, Multi-Modal Graph Neural Network (MM-GNN). | CS.cvpr | 2020-06-08 |
| 398 | Hierarchical Conditional Relation Networks For Video Question Answering | THAO MINH LE et. al. | We introduce a general-purpose reusable neural unit called Conditional Relation Network (CRN) that serves as a building block to construct more sophisticated structures for representation and reasoning over video. | CS.cvpr | 2020-06-08 |
| 399 | 12-in-1: Multi-Task Vision And Language Representation Learning | JIASEN LU et. al. | In this work, we investigate these relationships between vision-and-language tasks by developing a large-scale, multi-task model. | CS.cvpr | 2020-06-08 |
| 400 | Attention-Based Context Aware Reasoning For Situation Recognition | THILINI COORAY et. al. | Inspired by the success achieved by query-based visual reasoning (e.g., Visual Question Answering), we propose to address semantic role prediction as a query-based visual reasoning problem. | CS.cvpr | 2020-06-08 |
| 401 | X-Linear Attention Networks For Image Captioning | YINGWEI PAN et. al. | In this paper, we introduce a unified attention block — X-Linear attention block, that fully employs bilinear pooling to selectively capitalize on visual information or perform multi-modal reasoning. | CS.cvpr | 2020-06-08 |
| 402 | Counterfactual Vision And Language Learning | EHSAN ABBASNEJAD et. al. | We propose a method that addresses this problem by introducing counterfactuals in the training. | CS.cvpr | 2020-06-08 |
| 403 | Counterfactual Samples Synthesizing For Robust Visual Question Answering | LONG CHEN et. al. | To this end, we propose a model-agnostic Counterfactual Samples Synthesizing (CSS) training scheme. | CS.cvpr | 2020-06-08 |
| 404 | Pre-training Polish Transformer-based Language Models At Scale | SŁAWOMIR DADAS et. al. | In this study, we present two language models for Polish based on the popular BERT architecture. | CS.arxiv | 2020-06-07 |
| 405 | Language Models As Fact Checkers? | NAYEON LEE et. al. | In this paper, we leverage this implicit knowledge to create an effective end-to-end fact checker using a solely a language model, without any external knowledge or explicit retrieval components. | CS.arxiv | 2020-06-07 |
| 406 | SERank: Optimize Sequencewise Learning To Rank Using Squeeze-and-Excitation Network | RUIXING WANG et. al. | In this work, we propose an effective and efficient method named as SERank which is a Sequencewise Ranking model by using Squeeze-and-Excitation network to take advantage of cross-document information. | CS.arxiv | 2020-06-07 |
| 407 | Counterfactual VQA: A Cause-Effect Look At Language Bias | YULEI NIU et. al. | In this paper, we propose a novel cause-effect look at the language bias, where the bias is formulated as the direct effect of question on answer from the view of causal inference. | CS.arxiv | 2020-06-07 |
| 408 | A Cross-Task Analysis Of Text Span Representations | SHUBHAM TOSHNIWAL et. al. | In this paper, we conduct a comprehensive empirical evaluation of six span representation methods using eight pretrained language representation models across six tasks, including two tasks that we introduce. | CS.arxiv | 2020-06-06 |
| 409 | Subjective Question Answering: Deciphering The Inner Workings Of Transformers In The Realm Of Subjectivity | LUKAS MUTTENTHALER | In this work, I’ve exploited a recently released dataset for span-selection Question Answering, namely SubjQA. | CS.arxiv | 2020-06-02 |
| 410 | Open-Domain Question Answering With Pre-Constructed Question Spaces | JINFENG XIAO et. al. | We propose a novel algorithm with a reader-retriever structure that differs from both families. | CS.arxiv | 2020-06-02 |
| 411 | BERT Based Multilingual Machine Comprehension In English And Hindi | SOMIL GUPTA et. al. | We, therefore, present in this article, our experiments with m-BERT for MMC in zero-shot, mono-lingual (e.g. Hindi Question-Hindi Snippet) and cross-lingual (e.g. English QuestionHindi Snippet) fine-tune setups. | CS.arxiv | 2020-06-02 |
| 412 | Question Answering On Scholarly Knowledge Graphs | MOHAMAD YASER JARADEH et. al. | We present JarvisQA, a BERT based system to answer questions on tabular views of scholarly knowledge graphs. Furthermore, we present a preliminary dataset of related tables and a corresponding set of natural language questions. | CS.arxiv | 2020-06-02 |
| 413 | Probing Emergent Semantics In Predictive Agents Via Question Answering | ABHISHEK DAS et. al. | We propose question-answering as a general paradigm to decode and understand the representations that such agents develop, applying our method to two recent approaches to predictive modeling -action-conditional CPC (Guo et al., 2018) and SimCore (Gregor et al., 2019). | CS.arxiv | 2020-06-01 |
| 414 | Context-based Transformer Models For Answer Sentence Selection | IVANO LAURIOLA et. al. | In this paper, we analyze the role of the contextual information in the sentence selection task, proposing a Transformer based architecture that leverages two types of contexts, local and global. | CS.arxiv | 2020-06-01 |
| 415 | Multimodal Grid Features And Cell Pointers For Scene Text Visual Question Answering | LLUÍS GÓMEZ et. al. | This paper presents a new model for the task of scene text visual question answering, in which questions about a given image can only be answered by reading and understanding scene text that is present in it. | CS.arxiv | 2020-06-01 |
| 416 | Structured Multimodal Attentions For TextVQA | CHENYU GAO et. al. | In this paper, we propose a structured multimodal attention (SMA) neural network to solve the above issues. | CS.arxiv | 2020-06-01 |
| 417 | An Effective Contextual Language Modeling Framework For Speech Summarization With Augmented Features | SHI-YAN WENG et. al. | In view of this, we in this paper contextualize and enhance the state-of-the-art BERT-based model for speech summarization, while its contributions are at least three-fold. | CS.arxiv | 2020-06-01 |
| 418 | Conversational Machine Comprehension: A Literature Review | SOMIL GUPTA et. al. | It focuses on synthesizing a generic framework for CMC models, rather than describing the models individually. | CS.arxiv | 2020-05-31 |
| 419 | Efficient Deployment Of Conversational Natural Language Interfaces Over Databases | ANTHONY COLAS et. al. | In this work, we propose a novel method for accelerating the training dataset collection for developing the natural language-to-query-language machine learning models. | CS.arxiv | 2020-05-31 |
| 420 | Improving Quality Of A Post’s Set Of Answers In Stack Overflow | MOHAMMADREZAR TAVAKOLI et. al. | In this paper, we propose an approach to automate the identification process of such posts and boost their set of answers, utilizing the help of related experts. | CS.arxiv | 2020-05-30 |
| 421 | Using Large Pretrained Language Models For Answering User Queries From Product Specifications | KALYANI ROY et. al. | We propose an approach to automatically create a training dataset for this problem. | CS.arxiv | 2020-05-29 |
| 422 | Language Models Are Few-Shot Learners | TOM B. BROWN et. al. | Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting. | CS.arxiv | 2020-05-28 |
| 423 | English Intermediate-Task Training Improves Zero-Shot Cross-Lingual Transfer Too | JASON PHANG et. al. | We investigate whether English intermediate-task training is still helpful on non-English target tasks. | CS.arxiv | 2020-05-26 |
| 424 | Object-QA: Towards High Reliable Object Quality Assessment | JING LU et. al. | In this paper, we define the problem of object quality assessment for the first time and propose an effective approach named Object-QA to assess high-reliable quality scores for object images. | CS.arxiv | 2020-05-26 |
| 425 | Generating Semantically Valid Adversarial Questions For TableQA | YI ZHU et. al. | In this paper, we propose SAGE (Semantically valid Adversarial GEnerator), a Wasserstein sequence-to-sequence model for TableQA white-box attack. | CS.arxiv | 2020-05-26 |
| 426 | Refining Implicit Argument Annotation For UCCA | RUIXIANG CUI et. al. | In this paper, we design a typology for fine-grained implicit argument annotation on top of Universal Conceptual Cognitive Annotation’s foundational layer (Abend and Rappoport, 2013). | CS.arxiv | 2020-05-26 |
| 427 | Knowledge Graph Simple Question Answering For Unseen Domains | GEORGIOS SIDIROPOULOS et. al. | We propose a data-centric domain adaptation framework that consists of a KGSQA system that is applicable to new domains, and a sequence to sequence question generation method that automatically generates question-answer pairs for the new domain. | CS.arxiv | 2020-05-25 |
| 428 | An Audio-enriched BERT-based Framework For Spoken Multiple-choice Question Answering | CHIA-CHIH KUO et. al. | Consequently, an audio-enriched BERT-based SMCQA framework is proposed. | CS.arxiv | 2020-05-25 |
| 429 | History-Aware Question Answering In A Blocks World Dialogue System | BENJAMIN KANE et. al. | In this paper, we approach the problem of spatial memory in a multi-modal spoken dialogue system capable of answering questions about interaction history in a physical blocks world setting. | CS.arxiv | 2020-05-25 |
| 430 | Retrieval-Augmented Generation For Knowledge-Intensive NLP Tasks | PATRICK LEWIS et. al. | We introduce RAG models where the parametric memory is a pre-trained seq2seq model and the non-parametric memory is a dense vector index of Wikipedia, accessed with a pre-trained neural retriever. | CS.arxiv | 2020-05-22 |
| 431 | Comparative Study Of Machine Learning Models And BERT On SQuAD | DEVSHREE PATEL et. al. | This study aims to provide a comparative analysis of performance of certain models popular in machine learning and the BERT model on the Stanford Question Answering Dataset (SQuAD). | CS.arxiv | 2020-05-22 |
| 432 | A Complex KBQA System Using Multiple Reasoning Paths | KECHEN QIN et. al. | In this paper, we introduce an end-to-end KBQA system which can leverage multiple reasoning paths’ information and only requires labeled answer as supervision. | CS.arxiv | 2020-05-21 |
| 433 | RuBQ: A Russian Dataset For Question Answering Over Wikidata | VLADISLAV KORABLINOV et. al. | The paper presents RuBQ, the first Russian knowledge base question answering (KBQA) dataset. | CS.arxiv | 2020-05-21 |
| 434 | Functorial Language Games For Question Answering | GIOVANNI DE FELICE et. al. | We present some categorical investigations into Wittgenstein’s language-games, with applications to game-theoretic pragmatics and question-answering in natural language processing. | CS.arxiv | 2020-05-19 |
| 435 | On The Value Of Out-of-Distribution Testing: An Example Of Goodhart’s Law | DAMIEN TENEY et. al. | We provide short- and long-term solutions to avoid these pitfalls and realize the benefits of OOD evaluation. | CS.arxiv | 2020-05-19 |
| 436 | Matching Questions And Answers In Dialogues From Online Forums | QI JIA et. al. | This paper presents a QA matching model considering both distance information and dialogue history by two simultaneous attention mechanisms called mutual attention. Because existing dialogue datasets such as the Ubuntu dataset are not suitable for the QA matching task, we further create a dataset with 1,000 labeled dialogues and demonstrate that our proposed model outperforms the state-of-the-art and other strong baselines, particularly for matching long-distance QA pairs. | CS.arxiv | 2020-05-19 |
| 437 | Towards Question Format Independent Numerical Reasoning: A Set Of Prerequisite Tasks | SWAROOP MISHRA et. al. | In pursuit of this goal, we introduce NUMBERGAME, a multifaceted benchmark to evaluate model performance across numerical reasoning tasks of eight diverse formats. | CS.arxiv | 2020-05-18 |
| 438 | Question-Driven Summarization Of Answers To Consumer Health Questions | MAX SAVERY et. al. | Using answers provided by the National Library of Medicine’s consumer health question answering system, we present the MEDIQA Answer Summarization dataset, the first summarization collection containing question-driven summaries of answers to consumer health questions. | CS.arxiv | 2020-05-18 |
| 439 | Support-BERT: Predicting Quality Of Question-Answer Pairs In MSDN Using Deep Bidirectional Transformer | BHASKAR SEN et. al. | In this brief paper, we tackle the quality Q&A modeling problems from the community support websites using a recently developed deep learning model using bidirectional transformers. | CS.arxiv | 2020-05-17 |
| 440 | Context-Based Quotation Recommendation | ANSEL MACLAUGHLIN et. al. | We therefore propose a novel context-aware quote recommendation system which utilizes the content an author has already written to generate a ranked list of quotable paragraphs and spans of tokens from a given source document. | CS.arxiv | 2020-05-17 |
| 441 | CS-NLP Team At SemEval-2020 Task 4: Evaluation Of State-of-the-art NLP Deep Learning Architectures On Commonsense Reasoning Task | SIRWE SAEEDI et. al. | In this paper, we investigate a commonsense inference task that unifies natural language understanding and commonsense reasoning. | CS.arxiv | 2020-05-17 |
| 442 | Visual Relationship Detection Using Scene Graphs: A Survey | ANIKET AGARWAL et. al. | In this paper, we present a detailed survey on the various techniques for scene graph generation, their efficacy to represent visual relationships and how it has been used to solve various downstream tasks. | CS.arxiv | 2020-05-16 |
| 443 | COVID-Twitter-BERT: A Natural Language Processing Model To Analyse COVID-19 Content On Twitter | MARTIN MÜLLER et. al. | In this work, we release COVID-Twitter-BERT (CT-BERT), a transformer-based model, pretrained on a large corpus of Twitter messages on the topic of COVID-19. | CS.arxiv | 2020-05-15 |
| 444 | An Evaluation Of Recent Neural Sequence Tagging Models In Turkish Named Entity Recognition | GIZEM ARAS et. al. | 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. | CS.arxiv | 2020-05-14 |
| 445 | Recommending Themes For Ad Creative Design Via Visual-Linguistic Representations | YICHAO ZHOU et. al. | To automatically infer ad themes via such multimodal sources of information in past ad campaigns, we propose a theme (keyphrase) recommender system for ad creative strategists. | CS.www | 2020-05-13 |
| 446 | Entity-Enriched Neural Models For Clinical Question Answering | BHANU PRATAP SINGH RAWAT et. al. | We explore state-of-the-art neural models for question answering on electronic medical records and improve their ability to generalize better on previously unseen (paraphrased) questions at test time. | CS.arxiv | 2020-05-13 |
| 447 | Asking Questions The Human Way: Scalable Question-Answer Generation From Text Corpus | BANG LIU et. al. | In this paper, we propose Answer-Clue-Style-aware Question Generation (ACS-QG), which aims at automatically generating high-quality and diverse question-answer pairs from unlabeled text corpus at scale by imitating the way a human asks questions. | CS.www | 2020-05-13 |
| 448 | Complex Factoid Question Answering With A Free-Text Knowledge Graph | CHEN ZHAO et. al. | We introduce delft, a factoid question answering system which combines the nuance and depth of knowledge graph question answering approaches with the broader coverage of free-text. | CS.www | 2020-05-13 |
| 449 | Interpretable Complex Question Answering | SOUMEN CHAKRABARTI | We will review cross-community co-evolution of question answering (QA) with the advent of large-scale knowledge graphs (KGs), continuous representations of text and graphs, and deep sequence analysis. | CS.www | 2020-05-13 |
| 450 | Fast Computation Of Explanations For Inconsistency In Large-Scale Knowledge Graphs | TRUNG-KIEN TRAN et. al. | In this paper, we present a novel approach to dramatically speed up the process of detecting and explaining inconsistency in large KGs by exploiting KG abstractions that capture prominent data patterns. | CS.www | 2020-05-13 |
| 451 | Text-to-SQL Generation For Question Answering On Electronic Medical Records | PING WANG et. al. | Based on the widely used publicly available electronic medical database, we create a new large-scale Question-SQL pair dataset, named MIMICSQL, in order to perform the Question-to-SQL generation task in healthcare domain. | CS.www | 2020-05-13 |
| 452 | What Is Normal, What Is Strange, And What Is Missing In A Knowledge Graph: Unified Characterization Via Inductive Summarization | CALEB BELTH et. al. | In this work, we introduce a unified solution to KG characterization by formulating the problem as unsupervised KG summarization with a set of inductive, soft rules, which describe what is normal in a KG, and thus can be used to identify what is abnormal, whether it be strange or missing. | CS.www | 2020-05-13 |
| 453 | Condition Aware And Revise Transformer For Question Answering | XINYAN ZHAO et. al. | To alleviate the effect of defective condition values, this paper proposes condition aware and revise Transformer (CAR-Transformer). | CS.www | 2020-05-13 |
| 454 | Distant Supervision For Multi-Stage Fine-Tuning In Retrieval-Based Question Answering | YUQING XIE et. al. | In the context of this architecture, we present a data augmentation technique using distant supervision to automatically annotate paragraphs as either positive or negative examples to supplement existing training data, which are then used together to fine-tune BERT. | CS.www | 2020-05-13 |
| 455 | Voice-based Reformulation Of Community Answers | SIMONE FILICE et. al. | In this paper, we define the Answer Reformulation task and propose a novel solution to automatically reformulate a community provided answer making it suitable for a voice interaction. | CS.www | 2020-05-13 |
| 456 | Review-guided Helpful Answer Identification In E-commerce | WENXUAN ZHANG et. al. | In this paper, we propose the Review-guided Answer Helpfulness Prediction (RAHP) model that not only considers the interactions between QA pairs but also investigates the opinion coherence between the answer and crowds’ opinions reflected in the reviews, which is another important factor to identify helpful answers. | CS.www | 2020-05-13 |
| 457 | Do Not Let The History Haunt You — Mitigating Compounding Errors In Conversational Question Answering | ANGROSH MANDYA et. al. | In this paper, we find that compounding errors occur when using previously predicted answers at test time, significantly lowering the performance of CoQA systems. | CS.arxiv | 2020-05-12 |
| 458 | Quantum Annealing-Based Software Components: An Experimental Case Study With SAT Solving | TOM KRÜGER et. al. | In this paper, we perform a case study on how to augment existing software with quantum computational primitives for the Boolean satisfiability problem (SAT) implemented using a quantum annealer (QA). | CS.arxiv | 2020-05-11 |
| 459 | A Dataset For Statutory Reasoning In Tax Law Entailment And Question Answering | NILS HOLZENBERGER et. al. | To investigate the performance of natural language understanding approaches on statutory reasoning, we introduce a dataset, together with a legal-domain text corpus. | CS.arxiv | 2020-05-11 |
| 460 | Maximizing Information Gain In Partially Observable Environments Via Prediction Reward | YASH SATSANGI et. al. | Based on this insight we present deep anticipatory networks (DANs), which enables an agent to take actions to reduce its uncertainty without performing explicit belief inference. | CS.arxiv | 2020-05-11 |
| 461 | How Context Affects Language Models’ Factual Predictions | FABIO PETRONI et. al. | In this paper, we go a step further and integrate information from a retrieval system with a pre-trained language model in a purely unsupervised way. | CS.arxiv | 2020-05-10 |
| 462 | Where Is Linked Data In Question Answering Over Linked Data? | TOMMASO SORU et. al. | To this end, we propose the creation of new evaluation settings to leverage the advantages of the Semantic Web to achieve AI-complete question answering. | CS.arxiv | 2020-05-07 |
| 463 | COBRA: Contrastive Bi-Modal Representation Algorithm | VISHAAL UDANDARAO et. al. | In this paper, we present a novel framework COBRA that aims to train two modalities (image and text) in a joint fashion inspired by the Contrastive Predictive Coding (CPC) and Noise Contrastive Estimation (NCE) paradigms which preserve both inter and intra-class relationships. | CS.arxiv | 2020-05-07 |
| 464 | DramaQA: Character-Centered Video Story Understanding With Hierarchical QA | SEONGHO CHOI et. al. | In this paper, we propose a novel video question answering (Video QA) task, DramaQA, for a comprehensive understanding of the video story. | CS.arxiv | 2020-05-07 |
| 465 | CounQER: A System For Discovering And Linking Count Information In Knowledge Bases | SHRESTHA GHOSH et. al. | CounQER: A System For Discovering And Linking Count Information In Knowledge Bases | CS.arxiv | 2020-05-07 |
| 466 | MultiReQA: A Cross-Domain Evaluation For Retrieval Question Answering Models | MANDY GUO et. al. | This paper presents MultiReQA, anew multi-domain ReQA evaluation suite com-posed of eight retrieval QA tasks drawn from publicly available QA datasets. | CS.arxiv | 2020-05-05 |
| 467 | CAiRE-COVID: A Question Answering And Query-focused Multi-Document Summarization System For COVID-19 Scholarly Information Management | DAN SU et. al. | To address the requests, we propose our CAiRE-COVID, a neural-based system that uses open-domain question answering (QA) techniques combined with summarization techniques for mining the available scientific literature. | CS.arxiv | 2020-05-04 |
| 468 | DoQA — Accessing Domain-Specific FAQs Via Conversational QA | JON ANDER CAMPOS et. al. | The goal of this work is to build conversational Question Answering (QA) interfaces for the large body of domain-specific information available in FAQ sites. | CS.arxiv | 2020-05-04 |
| 469 | What-if I Ask You To Explain: Explaining The Effects Of Perturbations In Procedural Text | DHEERAJ RAJAGOPAL et. al. | We present QUARTET, a system that constructs such explanations from paragraphs, by modeling the explanation task as a multitask learning problem. | CS.arxiv | 2020-05-04 |
| 470 | Visual Question Answering With Prior Class Semantics | VIOLETTA SHEVCHENKO et. al. | We present a novel mechanism to embed prior knowledge in a model for visual question answering. | CS.arxiv | 2020-05-03 |
| 471 | Is Multihop QA In DiRe Condition? Measuring And Reducing Disconnected Reasoning | HARSH TRIVEDI et. al. | For a recent large-scale model (XLNet), we show that only 18% of its answer score is obtained through multifact reasoning, roughly the same as that of a simpler RNN baseline. | CS.arxiv | 2020-05-02 |
| 472 | ForecastQA: A Question Answering Challenge For Event Forecasting | WOOJEONG JIN et. al. | In this work, we formulate the forecasting problem as a restricted-domain, multiple-choice, question-answering (QA) task that simulates the forecasting scenario. | CS.arxiv | 2020-05-02 |
| 473 | UnifiedQA: Crossing Format Boundaries With A Single QA System | DANIEL KHASHABI et. al. | As evidence, we use the latest advances in language modeling to build a single pre-trained QA model, UnifiedQA, that performs surprisingly well across 17 QA datasets spanning 4 diverse formats. | CS.arxiv | 2020-05-02 |
| 474 | AVA: An Automatic EValuation Approach To Question Answering Systems | THUY VU et. al. | We introduce AVA, an automatic evaluation approach for Question Answering, which given a set of questions associated with Gold Standard answers, can estimate system Accuracy. To design, train and test AVA, we built multiple large training, development, and test sets on both public and industrial benchmarks. | CS.arxiv | 2020-05-02 |
| 475 | SEEK: Segmented Embedding Of Knowledge Graphs | WENTAO XU et. al. | To mitigate this problem, we propose a lightweight modeling framework that can achieve highly competitive relational expressiveness without increasing the model complexity. | CS.arxiv | 2020-05-02 |
| 476 | BERT-kNN: Adding A KNN Search Component To Pretrained Language Models For Better QA | NORA KASSNER et. al. | Our contributions are as follows: i) BERT-kNN outperforms BERT on cloze-style QA by large margins without any further training. | CS.arxiv | 2020-05-02 |
| 477 | Exploring And Predicting Transferability Across NLP Tasks | TU VU et. al. | In this paper, we conduct an extensive study of the transferability between 33 NLP tasks across three broad classes of problems (text classification, question answering, and sequence labeling). | CS.arxiv | 2020-05-02 |
| 478 | ProtoQA: A Question Answering Dataset For Prototypical Common-Sense Reasoning | MICHAEL BORATKO et. al. | After presenting multiple competitive baseline models, we find that human performance still exceeds model scores on all evaluation metrics with a meaningful gap, supporting the challenging nature of the task. | CS.arxiv | 2020-05-02 |
| 479 | From Zero To Hero: On The Limitations Of Zero-Shot Cross-Lingual Transfer With Multilingual Transformers | ANNE LAUSCHER et. al. | In this work, we analyze their limitations and show that cross-lingual transfer via massively multilingual transformers, much like transfer via cross-lingual word embeddings, is substantially less effective in resource-lean scenarios and for distant languages. | CS.arxiv | 2020-05-01 |
| 480 | Scalable Multi-Hop Relational Reasoning For Knowledge-Aware Question Answering | YANLIN FENG et. al. | In this paper, we propose a novel knowledge-aware approach that equips pre-trained language models (PTLMs) with a multi-hop relational reasoning module, named multi-hop graph relation network (MHGRN). | CS.arxiv | 2020-05-01 |
| 481 | Self-supervised Knowledge Triplet Learning For Zero-shot Question Answering | PRATYAY BANERJEE et. al. | In this work, we propose Knowledge Triplet Learning (KTL), a self-supervised task over knowledge graphs. | CS.arxiv | 2020-05-01 |
| 482 | Visuo-Lingustic Question Answering (VLQA) Challenge | SHAILAJA KEYUR SAMPAT et. al. | We propose a novel task to derive joint inference about a given image-text modality and compile the Visuo-Linguistic Question Answering (VLQA) challenge corpus in a question answering setting. | CS.arxiv | 2020-05-01 |
| 483 | Connecting The Dots: A Knowledgeable Path Generator For Commonsense Question Answering | PEIFENG WANG et. al. | In this paper, we augment a general commonsense QA framework with a knowledgeable path generator. | CS.arxiv | 2020-05-01 |
| 484 | How Do Decisions Emerge Across Layers In Neural Models? Interpretation With Differentiable Masking | NICOLA DE CAO et. al. | To deal with these challenges, we introduce Differentiable Masking. | CS.arxiv | 2020-04-30 |
| 485 | Progressively Pretrained Dense Corpus Index For Open-Domain Question Answering | WENHAN XIONG et. al. | In this work, we propose a simple and resource-efficient method to pretrain the paragraph encoder. | CS.arxiv | 2020-04-30 |
| 486 | MAD-X: An Adapter-Based Framework For Multi-Task Cross-Lingual Transfer | JONAS PFEIFFER et. al. | We propose MAD-X, an adapter-based framework that enables high portability and parameter-efficient transfer to arbitrary tasks and languages by learning modular language and task representations. | CS.arxiv | 2020-04-30 |
| 487 | Context Based Text-generation Using LSTM Networks | SIVASURYA SANTHANAM | Several methods of extracting the context vectors are proposed in this work. | CS.arxiv | 2020-04-30 |
| 488 | Exploiting Social Networks. Technological Trends (Habilitation Thesis) | ADRIAN IFTENE | The habilitation thesis presents two main directions: 1. | CS.arxiv | 2020-04-30 |
| 489 | KPQA: A Metric For Generative Question Answering Using Keyphrase Weights | HWANHEE LEE et. al. | To alleviate this problem, we propose a new metric for evaluating the correctness of GenQA. | CS.arxiv | 2020-04-30 |
| 490 | Dynamic Language Binding In Relational Visual Reasoning | THAO MINH LE et. al. | We present Language-binding Object Graph Network, the first neural reasoning method with dynamic relational structures across both visual and textual domains with applications in visual question answering. | CS.arxiv | 2020-04-30 |
| 491 | Look At The First Sentence: Position Bias In Question Answering | MIYOUNG KO et. al. | In this study, we hypothesize that when the distribution of the answer positions is highly skewed in the training set (e.g., answers lie only in the k-th sentence of each passage), QA models predicting answers as positions can learn spurious positional cues and fail to give answers in different positions. | CS.arxiv | 2020-04-30 |
| 492 | Question Rewriting For Conversational Question Answering | SVITLANA VAKULENKO et. al. | Our evaluation results indicate that the QR model we proposed achieves near human-level performance on both datasets and the gap in performance on the end-to-end conversational QA task is attributed mostly to the errors in QA. | CS.arxiv | 2020-04-30 |
| 493 | Robust Question Answering Through Sub-part Alignment | JIFAN CHEN et. al. | To make a more robust and understandable QA system, we model question answering as an alignment problem. | CS.arxiv | 2020-04-30 |
| 494 | HERO: Hierarchical Encoder For Video+Language Omni-representation Pre-training | LINJIE LI et. al. | We present HERO, a novel framework for large-scale video+language omni-representation learning. | CS.arxiv | 2020-04-30 |
| 495 | A Supervised Word Alignment Method Based On Cross-Language Span Prediction Using Multilingual BERT | MASAAKI NAGATA et. al. | We present a novel supervised word alignment method based on cross-language span prediction. | CS.arxiv | 2020-04-29 |
| 496 | Exploiting Structured Knowledge In Text Via Graph-Guided Representation Learning | TAO SHEN et. al. | In this work, we aim at equipping pre-trained language models with structured knowledge. | CS.arxiv | 2020-04-29 |
| 497 | Exploring Contextualized Neural Language Models For Temporal Dependency Parsing | HAYLEY ROSS et. al. | In this paper, we develop several variants of BERT-based temporal dependency parser, and show that BERT significantly improves temporal dependency parsing (Zhang and Xue, 2018a). | CS.arxiv | 2020-04-29 |
| 498 | Pragmatic Issue-Sensitive Image Captioning | ALLEN NIE et. al. | To address this, we propose Issue-Sensitive Image Captioning (ISIC). | CS.arxiv | 2020-04-29 |
| 499 | SubjQA: A Dataset For Subjectivity And Review Comprehension | JOHANNES BJERVA et. al. | We therefore investigate the relationship between subjectivity and QA, while developing a new dataset. We release an English QA dataset (SubjQA) based on customer reviews, containing subjectivity annotations for questions and answer spans across 6 distinct domains. | CS.arxiv | 2020-04-29 |
| 500 | The Effect Of Natural Distribution Shift On Question Answering Models | JOHN MILLER et. al. | We build four new test sets for the Stanford Question Answering Dataset (SQuAD) and evaluate the ability of question-answering systems to generalize to new data. | CS.arxiv | 2020-04-29 |
| 501 | Event Extraction By Answering (Almost) Natural Questions | XINYA DU et. al. | To avoid this issue, we introduce a new paradigm for event extraction by formulating it as a question answering (QA) task, which extracts the event arguments in an end-to-end manner. | CS.arxiv | 2020-04-28 |
| 502 | Empower Entity Set Expansion Via Language Model Probing | YUNYI ZHANG et. al. | In this study, we propose a novel iterative set expansion framework that leverages automatically generated class names to address the semantic drift issue. | CS.arxiv | 2020-04-28 |
| 503 | A Novel Attention-based Aggregation Function To Combine Vision And Language | MATTEO STEFANINI et. al. | In this paper, we propose a novel fully-attentive reduction method for vision and language. | CS.arxiv | 2020-04-27 |
| 504 | Knowledge Enhanced Latent Relevance Mining For Question Answering | D. WANG et. al. | In this paper, we propose to integrate commonsense from the external knowledge graphs (KGs) into the answer selector through a knowledge-aware context-based attention mechanism. | CS.icassp | 2020-04-26 |
| 505 | Challenge Closed-book Science Exam: A Meta-learning Based Question Answering System | XINYUE ZHENG et. al. | Inspired by the dual process theory in cognitive science, we propose a MetaQA framework, where system 1 is an intuitive meta-classifier and system 2 is a reasoning module. | CS.arxiv | 2020-04-26 |
| 506 | A Neural Document Language Modeling Framework For Spoken Document Retrieval | L. YEN et. al. | Targeting on enhancing the SDR performance, the paper concentrates on proposing a neural retrieval framework, which assembles the merits of using language modeling (LM) mechanism in SDR and leveraging the abstractive information learned by the language representation models. | CS.icassp | 2020-04-26 |
| 507 | GLUECoS : An Evaluation Benchmark For Code-Switched NLP | SIMRAN KHANUJA et. al. | We present an evaluation benchmark, GLUECoS, for code-switched languages, that spans several NLP tasks in English-Hindi and English-Spanish. | CS.arxiv | 2020-04-26 |
| 508 | Multi-Layer Content Interaction Through Quaternion Product For Visual Question Answering | L. SHI ET AL. | To solve the issue for the intermediate layers, we propose an efficient Quaternion Block Network (QBN) to learn interaction not only for the last layer but also for all intermediate layers simultaneously. | CS.icassp | 2020-04-26 |
| 509 | Improving Spoken Question Answering Using Contextualized Word Representation | D. SU AND P. FUNG | In this paper, we propose using contextualized word representations to mitigate the effects of ASR errors and pretraining on existing textual QA datasets to mitigate the data scarcity issue. | CS.icassp | 2020-04-26 |
| 510 | A Heterogeneous Graph With Factual, Temporal And Logical Knowledge For Question Answering Over Dynamic Contexts | WANJUN ZHONG et. al. | In this work, we propose a graph-based approach, where a heterogeneous graph is automatically built with factual knowledge of the context, temporal knowledge of the past states, and logical knowledge that combines human-curated knowledge bases and rule bases. | CS.arxiv | 2020-04-25 |
| 511 | MCQA: Multimodal Co-attention Based Network For Question Answering | ABHISHEK KUMAR et. al. | We present MCQA, a learning-based algorithm for multimodal question answering. | CS.arxiv | 2020-04-25 |
| 512 | Event-QA: A Dataset For Event-Centric Question Answering Over Knowledge Graphs | TARCÍSIO SOUZA COSTA et. al. | In this paper, we present the Event-QA dataset for answering event-centric questions over knowledge graphs. | CS.arxiv | 2020-04-24 |
| 513 | Template-Based Question Generation From Retrieved Sentences For Improved Unsupervised Question Answering | ALEXANDER R. FABBRI et. al. | We propose an unsupervised approach to training QA models with generated pseudo-training data. | CS.arxiv | 2020-04-24 |
| 514 | Lite Transformer With Long-Short Range Attention | ZHANGHAO WU et. al. | In this paper, we present an efficient mobile NLP architecture, Lite Transformer to facilitate deploying mobile NLP applications on edge devices. | CS.arxiv | 2020-04-24 |
| 515 | Contextualized Representations Using Textual Encyclopedic Knowledge | MANDAR JOSHI et. al. | We present a method to represent input texts by contextualizing them jointly with dynamically retrieved textual encyclopedic background knowledge from multiple documents. | CS.arxiv | 2020-04-24 |
| 516 | Question Answering Over Curated And Open Web Sources | RISHIRAJ SAHA ROY et. al. | This tutorial would cover the highlights of this really active period of growth for QA to give the audience a grasp over the families of algorithms that are currently being used. | CS.arxiv | 2020-04-24 |
| 517 | Rapidly Bootstrapping A Question Answering Dataset For COVID-19 | RAPHAEL TANG et. al. | We present CovidQA, the beginnings of a question answering dataset specifically designed for COVID-19, built by hand from knowledge gathered from Kaggle’s COVID-19 Open Research Dataset Challenge. | CS.arxiv | 2020-04-23 |
| 518 | Visual Question Answering Using Semantic Information From Image Descriptions | TASMIA TASRIN et. al. | Considering these, we propose a deep neural network model that uses an attention mechanism which utilizes image features, the natural language question asked and semantic knowledge extracted from the image to produce open-ended answers for the given questions. | CS.arxiv | 2020-04-23 |
| 519 | AmbigQA: Answering Ambiguous Open-domain Questions | SEWON MIN et. al. | In this paper, we introduce AmbigQA, a new open-domain question answering task which involves finding every plausible answer, and then rewriting the question for each one to resolve the ambiguity. | CS.arxiv | 2020-04-22 |
| 520 | TCNN: Triple Convolutional Neural Network Models For Retrieval-based Question Answering System In E-commerce | SHUANGYONG SONG et. al. | In this paper, we aim to improve an IR based e-commerce QA system-AliMe with proposed text matching models, including a basic Triple Convolutional Neural Network (TCNN) model and two Attention-based TCNN (ATCNN) models. | CS.arxiv | 2020-04-22 |
| 521 | Optimizing Knowledge Graphs Through Voting-based User Feedback | R. YANG et. al. | To address these issues, in this paper, we propose an interactive framework that refines and optimizes knowledge graphs through user votes. | CS.icde | 2020-04-20 |
| 522 | Software Test Automation Maturity — A Survey Of The State Of The Practice | YUQING WANG et. al. | In this paper, we present a test automation maturity survey serving as a self-assessment for practitioners. | CS.arxiv | 2020-04-20 |
| 523 | Word Embedding-based Text Processing For Comprehensive Summarization And Distinct Information Extraction | XIANGPENG WAN et. al. | In this paper, we propose two automated text processing frameworks specifically designed to analyze online reviews. | CS.arxiv | 2020-04-20 |
| 524 | Neural Abstractive Summarization With Structural Attention | TANYA CHOWDHURY et. al. | In this work, we present a hierarchical encoder based on structural attention to model such inter-sentence and inter-document dependencies. | CS.arxiv | 2020-04-20 |
| 525 | Fine-tuning Multi-hop Question Answering With Hierarchical Graph Network | GUANMING XIONG | In this paper, we present a two stage model for multi-hop question answering. | CS.arxiv | 2020-04-20 |
| 526 | Ktrain: A Low-Code Library For Augmented Machine Learning | ARUN S. MAIYA | We present ktrain, a low-code Python library that makes machine learning more accessible and easier to apply. | CS.arxiv | 2020-04-19 |
| 527 | Bridging Anaphora Resolution As Question Answering | YUFANG HOU | In this paper, we cast bridging anaphora resolution as question answering based on context. | CS.arxiv | 2020-04-16 |
| 528 | A Methodology For Creating Question Answering Corpora Using Inverse Data Annotation | JAN DERIU et. al. | In this paper, we introduce a novel methodology to efficiently construct a corpus for question answering over structured data. | CS.arxiv | 2020-04-16 |
| 529 | Learning Structured Embeddings Of Knowledge Graphs With Adversarial Learning Framework | JIEHANG ZENG et. al. | We present a learning method using generative adversarial architecture designed to embed the entities and relations of the knowledge graphs into a continuous vector space. | CS.arxiv | 2020-04-15 |
| 530 | HybridQA: A Dataset Of Multi-Hop Question Answering Over Tabular And Textual Data | WENHU CHEN et. al. | To fill in the gap, we present HybridQA https://github.com/wenhuchen/HybridQA, a new large-scale question-answering dataset that requires reasoning on heterogeneous information. | CS.arxiv | 2020-04-15 |
| 531 | PALM: Pre-training An Autoencoding&Autoregressive Language Model For Context-conditioned Generation | BIN BI et. al. | This work presents PALM with a novel scheme that jointly pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus, specifically designed for generating new text conditioned on context. | CS.arxiv | 2020-04-14 |
| 532 | A Simple Yet Strong Pipeline For HotpotQA | DIRK GROENEVELD et. al. | Our pipeline has three steps: 1) use BERT to identify potentially relevant sentences independently of each other; 2) feed the set of selected sentences as context into a standard BERT span prediction model to choose an answer; and 3) use the sentence selection model, now with the chosen answer, to produce supporting sentences. | CS.arxiv | 2020-04-14 |
| 533 | Adversarial Augmentation Policy Search For Domain And Cross-Lingual Generalization In Reading Comprehension | ADYASHA MAHARANA et. al. | We address this issue via RL and more efficient Bayesian policy search methods for automatically learning the best augmentation policy combinations of the transformation probability for each adversary in a large search space. | CS.arxiv | 2020-04-13 |
| 534 | YouMakeup VQA Challenge: Towards Fine-grained Action Understanding In Domain-Specific Videos | SHIZHE CHEN et. al. | In this paper, we present the challenge guidelines, the dataset used, and performances of baseline models on the two proposed tasks. | CS.arxiv | 2020-04-12 |
| 535 | Explaining Question Answering Models Through Text Generation | VERONICA LATCINNIK et. al. | In this work, we propose a model for multi-choice question answering, where a LM-based generator generates a textual hypothesis that is later used by a classifier to answer the question. | CS.arxiv | 2020-04-12 |
| 536 | Which Visual Questions Are Difficult To Answer? Analysis With Entropy Of Answer Distributions | KENTO TERAO et. al. | We propose a novel approach to identify the difficulty of visual questions for Visual Question Answering (VQA) without direct supervision or annotations to the difficulty. | CS.arxiv | 2020-04-12 |
| 537 | Unsupervised Commonsense Question Answering With Self-Talk | VERED SHWARTZ et. al. | We propose an unsupervised framework based on self-talk as a novel alternative to multiple-choice commonsense tasks. | CS.arxiv | 2020-04-11 |
| 538 | Exploring The Spatial Reasoning Ability Of Neural Models In Human IQ Tests | HYUNJAE KIM et. al. | In this work, we focus on spatial reasoning and explore the spatial understanding of neural models. Using well-defined rules, we constructed datasets that consist of various complexity levels. | CS.arxiv | 2020-04-11 |
| 539 | Rephrasing Visual Questions By Specifying The Entropy Of The Answer Distribution | KENTO TERAO et. al. | We propose two learning strategies to train the proposed model with the VQA v2 dataset, which has no ambiguity information. | CS.arxiv | 2020-04-10 |
| 540 | Towards Automatic Generation Of Questions From Long Answers | SHLOK KUMAR MISHRA et. al. | Therefore, we propose a novel evaluation benchmark to assess the performance of existing AQG systems for long-text answers. | CS.arxiv | 2020-04-10 |
| 541 | Dense Passage Retrieval For Open-Domain Question Answering | VLADIMIR KARPUKHIN et. al. | In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework. | CS.arxiv | 2020-04-10 |
| 542 | More Bang For Your Buck: Natural Perturbation For Robust Question Answering | DANIEL KHASHABI et. al. | As an alternative to the standard approach of addressing this issue by constructing training sets of completely new examples, we propose doing so via minimal perturbation of examples. | CS.arxiv | 2020-04-09 |
| 543 | A Multilingual Study Of Multi-Sentence Compression Using Word Vertex-Labeled Graphs And Integer Linear Programming | ELVYS LINHARES PONTES et. al. | This paper describes an Integer Linear Programming method for MSC using a vertex-labeled graph to select different keywords, with the goal of generating more informative sentences while maintaining their grammaticality. | CS.arxiv | 2020-04-09 |
| 544 | Automated Utterance Generation | SOHAM PARIKH et. al. | In this paper, we propose an utterance generation system which 1) uses extractive summarization to extract important sentences from the description, 2) uses multiple paraphrasing techniques to generate a diverse set of paraphrases of the title and summary sentences, and 3) selects good candidate paraphrases with the help of a novel candidate selection algorithm. | CS.arxiv | 2020-04-07 |
| 545 | What Do Models Learn From Question Answering Datasets? | PRIYANKA SEN et. al. | In this paper, we investigate if models are learning reading comprehension from QA datasets by evaluating BERT-based models across five datasets. | CS.arxiv | 2020-04-07 |
| 546 | Faithful Embeddings For Knowledge Base Queries | HAITIAN SUN et. al. | \emph{Query embedding} (QE) techniques have been recently proposed where KB entities and KB queries are represented jointly in an embedding space, supporting relaxation and generalization in KB inference. | CS.arxiv | 2020-04-07 |
| 547 | Variational Question-Answer Pair Generation For Machine Reading Comprehension | KAZUTOSHI SHINODA et. al. | We present a deep generative model of question-answer (QA) pairs for machine reading comprehension. | CS.arxiv | 2020-04-07 |
| 548 | Understanding Knowledge Gaps In Visual Question Answering: Implications For Gap Identification And Testing | GOONMEET BAJAJ et. al. | As an initial step towards better quantifying our understanding of the performance of VQA models, we use a taxonomy of Knowledge Gaps (KGs) to tag questions with one or more types of KGs. | CS.arxiv | 2020-04-07 |
| 549 | Inexpensive Domain Adaptation Of Pretrained Language Models: Case Studies On Biomedical NER And Covid-19 QA | NINA POERNER et. al. | We cover over 60% of the BioBERT-BERT F1 delta, at 5% of BioBERT’s CO_2 footprint and 2% of its cloud compute cost. | CS.arxiv | 2020-04-07 |
| 550 | Query Focused Multi-Document Summarization With Distant Supervision | YUMO XU et. al. | In this work, we leverage distant supervision from question answering where various resources are available to more explicitly capture the relationship between queries and documents. | CS.arxiv | 2020-04-06 |
| 551 | Enhancing Review Comprehension With Domain-Specific Commonsense | AARON TRAYLOR et. al. | In this paper, we introduce xSense, an effective system for review comprehension using domain-specific commonsense knowledge bases (xSense KBs). | CS.arxiv | 2020-04-06 |
| 552 | Knowledge Fusion And Semantic Knowledge Ranking For Open Domain Question Answering | PRATYAY BANERJEE et. al. | In our work, we learn a semantic knowledge ranking model to re-rank knowledge retrieved through Lucene based information retrieval systems. | CS.arxiv | 2020-04-06 |
| 553 | Reinforced Multi-task Approach For Multi-hop Question Generation | DEEPAK GUPTA et. al. | We employ multitask learning with the auxiliary task of answer-aware supporting fact prediction to guide the question generator. | CS.arxiv | 2020-04-05 |
| 554 | Learning To Recover Reasoning Chains For Multi-Hop Question Answering Via Cooperative Games | YUFEI FENG et. al. | We propose a cooperative game approach to deal with this problem, in which how the evidence passages are selected and how the selected passages are connected are handled by two models that cooperate to select the most confident chains from a large set of candidates (from distant supervision). We propose the new problem of learning to recover reasoning chains from weakly supervised signals, i.e., the question-answer pairs. For evaluation, we created benchmarks based on two multi-hop QA datasets, HotpotQA and MedHop; and hand-labeled reasoning chains for the latter. | CS.arxiv | 2020-04-05 |
| 555 | Natural Language Processing For Word Sense Disambiguation And Information Extraction | K. R. CHOWDHARY | The thesis presents a new approach for Word Sense Disambiguation using thesaurus. | CS.arxiv | 2020-04-05 |
| 556 | Mining Shape Of Expertise: A Novel Approach Based On Convolutional Neural Network | MAHDI DEHGHAN et. al. | In this study, we have proposed a new deep model for T-shaped experts finding based on Convolutional Neural Networks. | CS.arxiv | 2020-04-05 |
| 557 | TAPAS: Weakly Supervised Table Parsing Via Pre-training | JONATHAN HERZIG et. al. | In this paper, we present TAPAS, an approach to question answering over tables without generating logical forms. | CS.arxiv | 2020-04-05 |
| 558 | Evaluating Multimodal Representations On Visual Semantic Textual Similarity | OIER LOPEZ DE LACALLE et. al. | The long term goal of our research is to devise multimodal representation techniques that improve current inference capabilities. | CS.arxiv | 2020-04-04 |
| 559 | Talk To Papers: Bringing Neural Question Answering To Academic Search | TIANCHANG ZHAO et. al. | We introduce Talk to Papers, which exploits the recent open-domain question answering (QA) techniques to improve the current experience of academic search. | CS.arxiv | 2020-04-04 |
| 560 | Generating Rationales In Visual Question Answering | HAMMAD A. AYYUBI et. al. | Generating Rationales In Visual Question Answering | CS.arxiv | 2020-04-04 |
| 561 | Towards Query Logs For Privacy Studies: On Deriving Search Queries From Questions | ASIA J. BIEGA et. al. | In this work, we take a step towards understanding query formulation by tapping into the rich potential of community question answering (CQA) forums. We release a dataset of 7,000 question-query pairs from this study to facilitate further research on query understanding. | CS.arxiv | 2020-04-04 |
| 562 | Template-based Question Answering Using Recursive Neural Networks | RAM G ATHREYA et. al. | We propose a neural network-based approach to automatically learn and classify natural language questions into its corresponding template using recursive neural networks. | CS.arxiv | 2020-04-03 |
| 563 | R3: A Reading Comprehension Benchmark Requiring Reasoning Processes | RAN WANG et. al. | In this work, we propose a novel task of reading comprehension, in which a model is required to provide final answers and reasoning processes. We develop an annotation platform to facilitate TRMR’s annotation, and release the R3 dataset, a \textbf{R}eading comprehension benchmark \textbf{R}equiring \textbf{R}easoning processes. | CS.arxiv | 2020-04-02 |
| 564 | Pixel-BERT: Aligning Image Pixels With Text By Deep Multi-Modal Transformers | ZHICHENG HUANG et. al. | We propose Pixel-BERT to align image pixels with text by deep multi-modal transformers that jointly learn visual and language embedding in a unified end-to-end framework. | CS.arxiv | 2020-04-02 |
| 565 | A Case Study On Tool Support For Collaboration In Agile Development | FABIO CALEFATO et. al. | We report on a longitudinal case study conducted at the Italian site of a large software company to further our understanding of how development and communication tools can be improved to better support agile practices and collaboration. | CS.arxiv | 2020-04-01 |
| 566 | Unification-based Reconstruction Of Explanations For Science Questions | MARCO VALENTINO et. al. | The paper presents a framework to reconstruct explanations for multiple choices science questions through explanation-centred corpora. | CS.arxiv | 2020-03-31 |
| 567 | NukeBERT: A Pre-trained Language Model For Low Resource Nuclear Domain | AYUSH JAIN et. al. | In this paper, the Nuclear Bidirectional Encoder Representational Transformers (NukeBERT) is proposed, which incorporates a novel technique for building BERT vocabulary to make it suitable for tasks with less training data. | CS.arxiv | 2020-03-30 |
| 568 | P $\approx$ NP, At Least In Visual Question Answering | SHAILZA JOLLY et. al. | In this paper, we measure the potential confounding factors when polar and non-polar samples are used jointly to train a baseline VQA classifier, and compare it to an upper bound where the over-representation of polar questions is excluded from the training. | CS.arxiv | 2020-03-26 |
| 569 | Common-Knowledge Concept Recognition For SEVA | JITIN KRISHNAN et. al. | 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. | CS.arxiv | 2020-03-25 |
| 570 | Visual Question Answering For Cultural Heritage | PIETRO BONGINI et. al. | The advantages are twofold: on the one hand the cognitive burden of the visitor will decrease, limiting the flow of information to what the user actually wants to hear; and on the other hand it proposes the most natural way of interacting with a guide, favoring engagement. | CS.arxiv | 2020-03-22 |
| 571 | Linguistically Driven Graph Capsule Network For Visual Question Reasoning | QINGXING CAO et. al. | Inspired by the property of a capsule network that can carve a tree structure inside a regular convolutional neural network (CNN), we propose a hierarchical compositional reasoning model called the Linguistically driven Graph Capsule Network, where the compositional process is guided by the linguistic parse tree. | CS.arxiv | 2020-03-22 |
| 572 | Beheshti-NER: Persian Named Entity Recognition Using BERT | EHSAN TAHER et. al. | In this paper, we use the pre-trained deep bidirectional network, BERT, to make a model for named entity recognition in Persian. | CS.arxiv | 2020-03-19 |
| 573 | Joint Event Extraction Along Shortest Dependency Paths Using Graph Convolutional Networks | ALI BALALI et. al. | To address the two above-referred problems, we propose a novel joint event extraction framework that aims to extract multiple event triggers and arguments simultaneously by introducing shortest dependency path (SDP) in the dependency graph. | CS.arxiv | 2020-03-19 |
| 574 | QnAMaker: Data To Bot In 2 Minutes | PARAG AGRAWAL et. al. | We demonstrate QnAMaker, a service that creates a conversational layer over semi-structured data such as FAQ pages, product manuals, and support documents. | CS.arxiv | 2020-03-18 |
| 575 | Towards Ground Truth Evaluation Of Visual Explanations | AHMED OSMAN et. al. | In the present work, we propose instead to evaluate explanations in a restricted and controlled setup using a synthetic dataset of rendered 3D shapes. | CS.arxiv | 2020-03-16 |
| 576 | RSVQA: Visual Question Answering For Remote Sensing Data | SYLVAIN LOBRY et. al. | This paper introduces the task of visual question answering for remote sensing data (RSVQA). Using an automatic method introduced in this article, we built two datasets (using low and high resolution data) of image/question/answer triplets. | CS.arxiv | 2020-03-16 |
| 577 | TRANS-BLSTM: Transformer With Bidirectional LSTM For Language Understanding | ZHIHENG HUANG et. al. | In this paper, we investigate how these two modeling techniques can be combined to create a more powerful model architecture. | CS.arxiv | 2020-03-15 |
| 578 | Heterogeneous Relational Reasoning In Knowledge Graphs With Reinforcement Learning | MANDANA SAEBI et. al. | We address these problems by introducing a type-enhanced RL agent that uses the local neighborhood information for efficient path-based reasoning over knowledge graphs. | CS.arxiv | 2020-03-12 |
| 579 | Video2Commonsense: Generating Commonsense Descriptions To Enrich Video Captioning | ZHIYUAN FANG et. al. | We present the first work on generating commonsense captions directly from videos, to describe latent aspects such as intentions, effects, and attributes. | CS.arxiv | 2020-03-11 |
| 580 | Investigating Entity Knowledge In BERT With Simple Neural End-To-End Entity Linking | SAMUEL BROSCHEIT | In this study we investigate the following questions: (a) Can all those steps be learned jointly with a model for contextualized text-representations, i.e. BERT (Devlin et al., 2019)? | CS.arxiv | 2020-03-11 |
| 581 | TyDi QA: A Benchmark For Information-Seeking Question Answering In Typologically Diverse Languages | JONATHAN H. CLARK et. al. | We present TyDi QA—a question answering dataset covering 11 typologically diverse languages with 204K question-answer pairs. | CS.arxiv | 2020-03-10 |
| 582 | MQA: Answering The Question Via Robotic Manipulation | YUHONG DENG et. al. | In this paper,we propose a novel task of Manipulation Question Answering(MQA),a class of Question Answering (QA) task, where the robot is required to find the answer to the question by actively interacting with the environment via manipulation. | CS.arxiv | 2020-03-10 |
| 583 | Overview Of The CCKS 2019 Knowledge Graph Evaluation Track: Entity, Relation, Event And QA | XIANPEI HAN et. al. | In this paper, we give an overview of the knowledge graph evaluation tract at CCKS 2019. | CS.arxiv | 2020-03-08 |
| 584 | Knowledge Graphs And Knowledge Networks: The Story In Brief | AMIT SHETH et. al. | This article is an attempt to summarize the journey of KG for AI. | CS.arxiv | 2020-03-07 |
| 585 | Natural Language QA Approaches Using Reasoning With External Knowledge | CHITTA BARAL et. al. | In this paper, we present a survey of the recent work on them. | CS.arxiv | 2020-03-06 |
| 586 | Uncovering Hidden Semantics Of Set Information In Knowledge Bases | SHRESTHA GHOSH et. al. | In this paper we aim at uncovering this hidden knowledge. | CS.arxiv | 2020-03-06 |
| 587 | Noise Estimation Using Density Estimation For Self-Supervised Multimodal Learning | ELAD AMRANI et. al. | In this work, we show that the problem of noise estimation for multimodal data can be reduced to a multimodal density estimation task. | CS.arxiv | 2020-03-06 |
| 588 | Practical Annotation Strategies For Question Answering Datasets | BERNHARD KRATZWALD et. al. | To provide a remedy for practitioners, our objective is to develop heuristic rules for annotating a subset of questions, so that the annotation cost is reduced while maintaining both in- and out-of-domain performance. | CS.arxiv | 2020-03-06 |
| 589 | Zero-Shot Cross-Lingual Transfer With Meta Learning | FARHAD NOORALAHZADEH et. al. | We show that this challenging setup can be approached using meta-learning, where, in addition to training a source language model, another model learns to select which training instances are the most beneficial to the first. | CS.arxiv | 2020-03-05 |
| 590 | Talking-Heads Attention | NOAM SHAZEER et. al. | We introduce talking-heads attention – a variation on multi-head attention which includes linearprojections across the attention-heads dimension, immediately before and after the softmax operation.While inserting only a small number of additional parameters and a moderate amount of additionalcomputation, talking-heads attention leads to better perplexities on masked language modeling tasks, aswell as better quality when transfer-learning to language comprehension and question answering tasks. | CS.arxiv | 2020-03-05 |
| 591 | A Study On Efficiency, Accuracy And Document Structure For Answer Sentence Selection | DANIELE BONADIMAN et. al. | In this paper, we argue that by exploiting the intrinsic structure of the original rank together with an effective word-relatedness encoder, we can achieve competitive results with respect to the state of the art while retaining high efficiency. | CS.arxiv | 2020-03-04 |
| 592 | A Study On Multimodal And Interactive Explanations For Visual Question Answering | KAMRAN ALIPOUR et. al. | We evaluate multimodal explanations in the setting of a Visual Question Answering (VQA) task, by asking users to predict the response accuracy of a VQA agent with and without explanations. | CS.arxiv | 2020-03-01 |
| 593 | AraBERT: Transformer-based Model For Arabic Language Understanding | WISSAM ANTOUN et. al. | In this paper, we pre-trained BERT specifically for the Arabic language in the pursuit of achieving the same success that BERT did for the English language. | CS.arxiv | 2020-02-28 |
| 594 | DC-BERT: Decoupling Question And Document For Efficient Contextual Encoding | YUYU ZHANG et. al. | To address the efficiency problem, we propose DC-BERT, a decoupled contextual encoding framework that has dual BERT models: an online BERT which encodes the question only once, and an offline BERT which pre-encodes all the documents and caches their encodings. | CS.arxiv | 2020-02-28 |
| 595 | Generating Followup Questions For Interpretable Multi-hop Question Answering | CHRISTOPHER MALON et. al. | We propose a framework for answering open domain multi-hop questions in which partial information is read and used to generate followup questions, to finally be answered by a pretrained single-hop answer extractor. | CS.arxiv | 2020-02-27 |
| 596 | Unshuffling Data For Improved Generalization | DAMIEN TENEY et. al. | We show that the common practice of mixing and shuffling training examples when training deep neural networks is not optimal. | CS.arxiv | 2020-02-26 |
| 597 | Exploring BERT Parameter Efficiency On The Stanford Question Answering Dataset V2.0 | ERIC HULBURD | In this paper we explore the parameter efficiency of BERT arXiv:1810.04805 on version 2.0 of the Stanford Question Answering dataset (SQuAD2.0). | CS.arxiv | 2020-02-25 |
| 598 | End-to-End Entity Linking And Disambiguation Leveraging Word And Knowledge Graph Embeddings | ROSTISLAV NEDELCHEV et. al. | Based on this idea, we propose the first end-to-end neural network approach that employs KG as well as word embeddings to perform joint relation and entity classification of simple questions while implicitly performing entity disambiguation with the help of a novel gating mechanism. | CS.arxiv | 2020-02-25 |
| 599 | Multimodal Transformer With Pointer Network For The DSTC8 AVSD Challenge | HUNG LE et. al. | In this work, we describe our submission to the AVSD track of the 8th Dialogue System Technology Challenge. | CS.arxiv | 2020-02-25 |
| 600 | Predicting Subjective Features From Questions On QA Websites Using BERT | ISSA ANNAMORADNEJAD et. al. | Therefore, with the overall goal of providing solutions for automating moderation actions in Q&A websites, we aim to provide a model to predict 20 quality or subjective aspects of questions in QA websites. | CS.arxiv | 2020-02-24 |
| 601 | FONDUE: A Framework For Node Disambiguation Using Network Embeddings | AHMAD MEL et. al. | This can be valuable for a range of purposes from the study of information diffusion to bibliographic analysis, bioinformatics research, and question-answering. | CS.arxiv | 2020-02-24 |
| 602 | Do Multi-Hop Question Answering Systems Know How To Answer The Single-Hop Sub-Questions? | YIXUAN TANG et. al. | In this paper, we investigate whether top-performing models for multi-hop questions understand the underlying sub-questions like humans. | CS.arxiv | 2020-02-23 |
| 603 | Unsupervised Question Decomposition For Question Answering | ETHAN PEREZ et. al. | Specifically, we propose an algorithm for One-to-N Unsupervised Sequence transduction (ONUS) that learns to map one hard, multi-hop question to many simpler, single-hop sub-questions. | CS.arxiv | 2020-02-22 |
| 604 | Is Aligning Embedding Spaces A Challenging Task? A Study On Heterogeneous Embedding Alignment Methods | RUSSA BISWAS et. al. | This paper provides a theoretical analysis and comparison of the state-of-the-art alignment methods between two embedding spaces representing entity-entity and entity-word. | CS.arxiv | 2020-02-21 |
| 605 | Training Question Answering Models From Synthetic Data | RAUL PURI et. al. | This work aims to narrow this gap by taking advantage of large language models and explores several factors such as model size, quality of pretrained models, scale of data synthesized, and algorithmic choices. | CS.arxiv | 2020-02-21 |
| 606 | Interactive Natural Language-based Person Search | VIKRAM SHREE et. al. | In this work, we consider the problem of searching people in an unconstrained environment, with natural language descriptions. | CS.arxiv | 2020-02-19 |
| 607 | Neural Relation Prediction For Simple Question Answering Over Knowledge Graph | AMIN ABOLGHASEMI et. al. | 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. | CS.arxiv | 2020-02-18 |
| 608 | SentenceMIM: A Latent Variable Language Model | MICHA LIVNE et. al. | We introduce sentenceMIM, a probabilistic auto-encoder for language modelling, trained with Mutual Information Machine (MIM) learning. | CS.arxiv | 2020-02-18 |
| 609 | CQ-VQA: Visual Question Answering On Categorized Questions | AAKANSHA MISHRA et. al. | This paper proposes CQ-VQA, a novel 2-level hierarchical but end-to-end model to solve the task of visual question answering (VQA). | CS.arxiv | 2020-02-17 |
| 610 | Text-based Question Answering From Information Retrieval And Deep Neural Network Perspectives: A Survey | ZAHRA ABBASIANTAEB et. al. | In this paper, we provide a comprehensive overview of different models proposed for the QA task, including both traditional information retrieval perspective, and more recent deep neural network perspective. We also introduce well-known datasets for the task and present available results from the literature to have a comparison between different techniques. | CS.arxiv | 2020-02-16 |
| 611 | Stress Test Evaluation Of Transformer-based Models In Natural Language Understanding Tasks | CARLOS ASPILLAGA et. al. | For that reason, this work evaluates three Transformer-based models (RoBERTa, XLNet, and BERT) in Natural Language Inference (NLI) and Question Answering (QA) tasks to know if they are more robust or if they have the same flaws as their predecessors. | CS.arxiv | 2020-02-14 |
| 612 | FQuAD: French Question Answering Dataset | MARTIN D’HOFFSCHMIDT et. al. | In the present work, we introduce the French Question Answering Dataset (FQuAD). | CS.arxiv | 2020-02-14 |
| 613 | Sparse And Structured Visual Attention | PEDRO HENRIQUE MARTINS et. al. | In this paper, to better link the image structure with the text, we replace the traditional softmax attention mechanism with two alternative sparsity-promoting transformations: sparsemax, which is able to select the relevant regions only (assigning zero weight to the rest), and a newly proposed Total-Variation Sparse Attention (TVmax), which further encourages the joint selection of adjacent spatial locations. | CS.arxiv | 2020-02-13 |
| 614 | Component Analysis For Visual Question Answering Architectures | CAMILA KOLLING et. al. | The main goal of this paper is to provide a comprehensive analysis regarding the impact of each component in VQA models. | CS.arxiv | 2020-02-12 |
| 615 | Outlier Guided Optimization Of Abdominal Segmentation | YUCHEN XU et. al. | Herein, we propose a single-pass active learning method through human quality assurance (QA). | CS.arxiv | 2020-02-10 |
| 616 | HHH: An Online Medical Chatbot System Based On Knowledge Graph And Hierarchical Bi-Directional Attention | QIMING BAO et. al. | This paper proposes a chatbot framework that adopts a hybrid model which consists of a knowledge graph and a text similarity model. | CS.arxiv | 2020-02-08 |
| 617 | Joint Learning Of Answer Selection And Answer Summary Generation In Community Question Answering | YANG DENG et. al. | To solve these problems, we tackle the tasks of answer selection and answer summary generation in CQA with a novel joint learning model. In addition, we construct a new large-scale CQA corpus, WikiHowQA, which contains long answers for answer selection as well as reference summaries for answer summarization. | CS.aaai | 2020-02-07 |
| 618 | PIQA: Reasoning About Physical Commonsense In Natural Language | YONATAN BISK et. al. | In this paper, we introduce the task of physical commonsense reasoning and a corresponding benchmark dataset Physical Interaction: Question Answering or PIQA. | CS.aaai | 2020-02-07 |
| 619 | Re-Attention For Visual Question Answering | WENYA GUO et. al. | In this paper, to utilize the information in answer, we propose a re-attention framework for the VQA task. | CS.aaai | 2020-02-07 |
| 620 | Location-Aware Graph Convolutional Networks For Video Question Answering | DENG HUANG et. al. | In this work, we propose to represent the contents in the video as a location-aware graph by incorporating the location information of an object into the graph construction. | CS.aaai | 2020-02-07 |
| 621 | Getting Closer To AI Complete Question Answering: A Set Of Prerequisite Real Tasks | ANNA ROGERS et. al. | We present QuAIL, the first RC dataset to combine text-based, world knowledge and unanswerable questions, and to provide question type annotation that would enable diagnostics of the reasoning strategies by a given QA system. | CS.aaai | 2020-02-07 |
| 622 | One-Shot Learning For Long-Tail Visual Relation Detection | WEITAO WANG et. al. | With this in mind, we designed a novel model for visual relation detection that works in one-shot settings. | CS.aaai | 2020-02-07 |
| 623 | Description Based Text Classification With Reinforcement Learning | DUO CHAI et. al. | Inspired by the current trend of formalizing NLP problems as question answering tasks, we propose a new framework for text classification, in which each category label is associated with a category description. | CS.arxiv | 2020-02-07 |
| 624 | Evaluating Commonsense In Pre-Trained Language Models | XUHUI ZHOU et. al. | We study the commonsense ability of GPT, BERT, XLNet, and RoBERTa by testing them on seven challenging benchmarks, finding that language modeling and its variants are effective objectives for promoting models’ commonsense ability while bi-directional context and larger training set are bonuses. We release a test set, named CATs publicly, for future research. | CS.aaai | 2020-02-07 |
| 625 | Reasoning With Heterogeneous Graph Alignment For Video Question Answering | PIN JIANG et. al. | We propose a deep heterogeneous graph alignment network over the video shots and question words. | CS.aaai | 2020-02-07 |
| 626 | ManyModalQA: Modality Disambiguation And QA Over Diverse Inputs | DARRYL HANNAN et. al. | We present a new multimodal question answering challenge, ManyModalQA, in which an agent must answer a question by considering three distinct modalities: text, images, and tables. We collect our data by scraping Wikipedia and then utilize crowdsourcing to collect question-answer pairs. | CS.aaai | 2020-02-07 |
| 627 | KnowIT VQA: Answering Knowledge-Based Questions About Videos | NOA GARCIA et. al. | We propose a novel video understanding task by fusing knowledge-based and video question answering. | CS.aaai | 2020-02-07 |
| 628 | End-to-End Argumentation Knowledge Graph Construction | KHALID AL-KHATIB et. al. | Original in our work is that we propose a model of the knowledge encapsulated in arguments. Based on this model, we build a new corpus that comprises about 16k manual annotations of 4740 claims with instances of the model’s elements, and we develop an end-to-end framework that automatically identifies all modeled types of instances. | CS.aaai | 2020-02-07 |
| 629 | DualVD: An Adaptive Dual Encoding Model For Deep Visual Understanding In Visual Dialogue | XIAOZE JIANG et. al. | In this research, we propose a novel model to depict an image from both visual and semantic perspectives. | CS.aaai | 2020-02-07 |
| 630 | MMM: Multi-Stage Multi-Task Learning For Multi-Choice Reading Comprehension | DI JIN et. al. | We introduce MMM, a Multi-stage Multi-task learning framework for Multi-choice reading comprehension. | CS.aaai | 2020-02-07 |
| 631 | Learning To Interactively Learn And Assist | MARK WOODWARD et. al. | In this paper, we propose such interactive learning as an alternative to reward or demonstration-driven learning. | CS.aaai | 2020-02-07 |
| 632 | JEC-QA: A Legal-Domain Question Answering Dataset | HAOXI ZHONG et. al. | We present JEC-QA, the largest question answering dataset in the legal domain, collected from the National Judicial Examination of China. | CS.aaai | 2020-02-07 |
| 633 | Divide And Conquer: Question-Guided Spatio-Temporal Contextual Attention For Video Question Answering | JIANWEN JIANG et. al. | To tackle this problem, we propose a Question-Guided Spatio-Temporal Contextual Attention Network (QueST) method. | CS.aaai | 2020-02-07 |
| 634 | Multi-Task Learning With Generative Adversarial Training For Multi-Passage Machine Reading Comprehension | QIYU REN et. al. | In this paper, we present MG-MRC, a novel approach for multi-passage MRC via multi-task learning with generative adversarial training. | CS.aaai | 2020-02-07 |
| 635 | V-PROM: A Benchmark For Visual Reasoning Using Visual Progressive Matrices | DAMIEN TENEY et. al. | We propose a new large-scale benchmark to evaluates abstract reasoning over real visual data. | CS.aaai | 2020-02-07 |
| 636 | ReCO: A Large Scale Chinese Reading Comprehension Dataset On Opinion | BINGNING WANG et. al. | This paper presents the ReCO, a human-curated Chinese Reading Comprehension dataset on Opinion. | CS.aaai | 2020-02-07 |
| 637 | What Do You Mean ‘Why?’: Resolving Sluices In Conversations | VICTOR PETRÉN BACH HANSEN et. al. | This paper introduces the novel ellipsis resolution task of resolving such one-word questions, referred to as sluices in linguistics. We present a crowd-sourced dataset containing annotations of sluices from over 4,000 dialogues collected from conversational QA datasets, as well as a series of strong baseline architectures. | CS.aaai | 2020-02-07 |
| 638 | QASC: A Dataset For Question Answering Via Sentence Composition | TUSHAR KHOT et. al. | Guided by these annotations, we present a two-step approach to mitigate the retrieval challenges. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition (QASC), that requires retrieving facts from a large corpus and composing them to answer a multiple-choice question. | CS.aaai | 2020-02-07 |
| 639 |