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 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 | 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 |
| 2 | 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.arxiv | 2020-05-11 |
| 3 | 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 |
| 4 | 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 |
| 5 | 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.arxiv | 2020-05-08 |
| 6 | 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.arxiv | 2020-05-08 |
| 7 | 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 |
| 8 | 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 |
| 9 | 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 |
| 10 | 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.arxiv | 2020-05-07 |
| 11 | 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 |
| 12 | 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.arxiv | 2020-05-06 |
| 13 | 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 |
| 14 | 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.arxiv | 2020-05-05 |
| 15 | 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 |
| 16 | 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.arxiv | 2020-05-04 |
| 17 | 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 |
| 18 | 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) a stopping criterion that terminates retrieval when the terms in the given question and candidate answers are covered by the retrieved justifications. | CS.arxiv | 2020-05-03 |
| 19 | 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 |
| 20 | 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 |
| 21 | BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA | NORA KASSNER et. al. | Our contributions are as follows. | CS.arxiv | 2020-05-02 |
| 22 | 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.arxiv | 2020-05-02 |
| 23 | 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 |
| 24 | ForecastQA: Machine Comprehension of Temporal Text for Answering Forecasting Questions | WOOJEONG JIN et. al. | In this paper, we introduce ForecastQA, a new open-domain question answering dataset consisting of 10k questions which requires temporal reasoning. | CS.arxiv | 2020-05-02 |
| 25 | Measuring and Reducing Non-Multifact Reasoning in Multi-hop Question Answering | HARSH TRIVEDI et. al. | To this end, we introduce an automated sufficiency-based dataset transformation that considers all possible partitions of supporting facts, capturing disconnected reasoning. | CS.arxiv | 2020-05-02 |
| 26 | ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning | MICHAEL BORATKO et. al. | This paper introduces a new question answering dataset for training and evaluating common-sense reasoning capabilities of artificial intelligence systems in such prototypical situations. | CS.arxiv | 2020-05-02 |
| 27 | 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 |
| 28 | 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 |
| 29 | 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.arxiv | 2020-05-01 |
| 30 | Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering | PEIFENG WANG et. al. | In this paper, we propose to learn a multi-hop knowledge path generator to generate structured evidence dynamically according to the questions. | CS.arxiv | 2020-05-01 |
| 31 | Diverse Visuo-Lingustic Question Answering (DVLQA) Challenge | SHAILAJA SAMPAT et. al. | Diverse Visuo-Lingustic Question Answering (DVLQA) Challenge | CS.arxiv | 2020-05-01 |
| 32 | 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 |
| 33 | 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.arxiv | 2020-05-01 |
| 34 | 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 PTLMs with a multi-hop relational reasoning module, named multi-hop graph relation networks (MHGRN). | CS.arxiv | 2020-05-01 |
| 35 | Self-supervised Knowledge Triplet Learning for Zero-shot Question Answering | PRATYAY BANERJEE et. al. | In this work, we propose Knowledge Triplet Learning, a self-supervised task over knowledge graphs. | CS.arxiv | 2020-05-01 |
| 36 | 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 |
| 37 | 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 |
| 38 | Exploiting Social Networks. Technological Trends (Habilitation Thesis) | ADRIAN IFTENE | The habilitation thesis presents two main directions: 1. | CS.arxiv | 2020-04-30 |
| 39 | HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training | LINJIE LI et. al. | We present HERO, a Hierarchical EncodeR for Omni-representation learning, for large-scale video+language pre-training. | CS.arxiv | 2020-04-30 |
| 40 | How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking | NICOLA DE CAO et. al. | To deal with these two challenges, we introduce Differentiable Masking. | CS.arxiv | 2020-04-30 |
| 41 | KPQA: A Metric for Generative Question Answering Using Word 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 |
| 42 | 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 learn spurious positional cues and fail to give answers in different positions. | CS.arxiv | 2020-04-30 |
| 43 | 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 |
| 44 | 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 |
| 45 | Question Rewriting for Conversational Question Answering | SVITLANA VAKULENKO et. al. | We address the conversational QA task by decomposing it into question rewriting and question answering subtasks, and conduct a systematic evaluation of this approach on two publicly available datasets. | CS.arxiv | 2020-04-30 |
| 46 | 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 |
| 47 | A Focused Study to Compare Arabic Pre-training Models on Newswire IE Tasks | WUWEI LAN et. al. | In this work, we pre-train a Gigaword-based bilingual language model (GigaBERT) to study these two distant languages as well as zero-short transfer learning on the information extraction tasks. | CS.arxiv | 2020-04-29 |
| 48 | 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 |
| 49 | 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.arxiv | 2020-04-29 |
| 50 | 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 |
| 51 | Exploring Contextualized Neural Language Models for Temporal Dependency Parsing | HAYLEY ROSS et. al. | In this paper, we developed 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 |
| 52 | Pragmatic Issue-Sensitive Image Captioning | ALLEN NIE et. al. | To address this, we propose Issue-Sensitive Image Captioning (ISIC). | CS.arxiv | 2020-04-29 |
| 53 | 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.arxiv | 2020-04-29 |
| 54 | 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 |
| 55 | 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 |
| 56 | 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 |
| 57 | 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 |
| 58 | 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.arxiv | 2020-04-28 |
| 59 | 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 |
| 60 | 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.arxiv | 2020-04-27 |
| 61 | 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 |
| 62 | 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 |
| 63 | 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 |
| 64 | 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 |
| 65 | 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 |
| 66 | 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.arxiv | 2020-04-26 |
| 67 | 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 |
| 68 | 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 |
| 69 | 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.arxiv | 2020-04-25 |
| 70 | 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 |
| 71 | 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 |
| 72 | Event-QA: A Dataset for Event-Centric Question Answering over Knowledge Graphs | TARC�SIO 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 |
| 73 | 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 |
| 74 | 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 |
| 75 | Revisiting Modulated Convolutions for Visual Counting and Beyond | DUY-KIEN NGUYEN et. al. | In this paper, we propose a simple and effective alternative for visual counting by revisiting modulated convolutions that fuse query and image locally. | CS.arxiv | 2020-04-24 |
| 76 | 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 |
| 77 | 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 |
| 78 | 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 |
| 79 | 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 predicting a set of question-answer pairs, where every plausible answer is paired with a disambiguated rewrite of the original question. | CS.arxiv | 2020-04-22 |
| 80 | 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 |
| 81 | 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.arxiv | 2020-04-21 |
| 82 | 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 |
| 83 | 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 |
| 84 | 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 |
| 85 | 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.arxiv | 2020-04-19 |
| 86 | 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 |
| 87 | 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.arxiv | 2020-04-19 |
| 88 | 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 |
| 89 | 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 |
| 90 | HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data | WENHU CHEN et. al. | To fill in the gap, we present \dataset, a new large-scale question-answering dataset that requires reasoning on heterogeneous information. | CS.arxiv | 2020-04-15 |
| 91 | 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 |
| 92 | 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 |
| 93 | 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 |
| 94 | A negative case analysis of visual grounding methods for VQA | ROBIK SHRESTHA et. al. | To address this issue, recent bias mitigation methods for VQA propose to incorporate visual cues (e.g., human attention maps) to better ground the VQA models, showcasing impressive gains. | CS.arxiv | 2020-04-12 |
| 95 | 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 |
| 96 | 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 |
| 97 | 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 |
| 98 | 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 |
| 99 | Unsupervised Commonsense Question Answering with Self-Talk | VERED SHWARTZ et. al. | We propose an unsupervised framework based on \emph{self-talk} as a novel alternative to multiple-choice commonsense tasks. | CS.arxiv | 2020-04-11 |
| 100 | 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 |
| 101 | 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 |
| 102 | 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 |
| 103 | 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 |
| 104 | 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.arxiv | 2020-04-09 |
| 105 | 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 |
| 106 | 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 |
| 107 | Guessing What’s Plausible But Remembering What’s True: Accurate Neural Reasoning for Question-Answering | HAITIAN SUN et. al. | Our approach introduces two new mechanisms for KB reasoning: neural retrieval over a set of embedded triples, and memorization of highly specific information with a compact sketch structure. | CS.arxiv | 2020-04-07 |
| 108 | Inexpensive Domain Adaptation of Pretrained Language Models: Case Studies on Biomedical NER and Covid-19 QA | NINA POERNER et. al. | We cover over 50% 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 |
| 109 | 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.arxiv | 2020-04-07 |
| 110 | Understanding Knowledge Gaps in Visual Question Answering: Implications for Gap Identification and Testing | GOONMEET BAJAJ et. al. | In order to reduce the skew in the distribution of questions across KGs, we introduce a targeted question generation model. | CS.arxiv | 2020-04-07 |
| 111 | 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 |
| 112 | What do Models Learn from Question Answering Datasets? | PRIYANKA SEN et. al. | In this paper, we investigate what models are really learning from QA datasets by evaluating BERT-based models across five popular QA datasets. | CS.arxiv | 2020-04-07 |
| 113 | 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 |
| 114 | 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 |
| 115 | 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.arxiv | 2020-04-06 |
| 116 | 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 |
| 117 | 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 |
| 118 | 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 |
| 119 | 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 |
| 120 | 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 |
| 121 | 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 |
| 122 | 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 |
| 123 | Generating Rationales in Visual Question Answering | HAMMAD A. AYYUBI et. al. | Generating Rationales in Visual Question Answering | CS.arxiv | 2020-04-04 |
| 124 | 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 |
| 125 | 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 |
| 126 | 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 |
| 127 | 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 |
| 128 | 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 |
| 129 | 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.arxiv | 2020-03-31 |
| 130 | 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 |
| 131 | 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.arxiv | 2020-03-31 |
| 132 | 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 |
| 133 | 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.arxiv | 2020-03-27 |
| 134 | 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 |
| 135 | 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 |
| 136 | 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.arxiv | 2020-03-23 |
| 137 | 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 |
| 138 | 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 |
| 139 | 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 |
| 140 | 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 |
| 141 | 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.arxiv | 2020-03-19 |
| 142 | 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 |
| 143 | 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 |
| 144 | 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 |
| 145 | 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 |
| 146 | Counterfactual Samples Synthesizing for Robust Visual Question Answering | LONG CHEN et. al. | To reduce the language biases, several recent works introduce an auxiliary question-only model to regularize the training of targeted VQA model, and achieve dominating performance on VQA-CP. | CS.arxiv | 2020-03-14 |
| 147 | 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.arxiv | 2020-03-13 |
| 148 | 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 |
| 149 | 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 |
| 150 | Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning | ZHIYUAN FANG et. al. | We present the first work on generating \textit{commonsense} captions directly from videos, in order to describe latent aspects such as intentions, attributes, and effects. | CS.arxiv | 2020-03-11 |
| 151 | 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 |
| 152 | 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 |
| 153 | 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 |
| 154 | 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 |
| 155 | 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 |
| 156 | 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 |
| 157 | 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 |
| 158 | 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 |
| 159 | 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 |
| 160 | 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 |
| 161 | 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 |
| 162 | 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 |
| 163 | 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 |
| 164 | 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 |
| 165 | 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 |
| 166 | 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 |
| 167 | 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 |
| 168 | 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 |
| 169 | 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.arxiv | 2020-02-25 |
| 170 | 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 |
| 171 | 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 |
| 172 | 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.arxiv | 2020-02-24 |
| 173 | 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 |
| 174 | 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 |
| 175 | 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 |
| 177 | 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 |
| 178 | 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 |
| 179 | VQA-LOL: Visual Question Answering under the Lens of Logic | TEJAS GOKHALE et. al. | In this paper, we investigate visual question answering (VQA) through the lens of logical transformation and posit that systems that seek to answer questions about images must be robust to these transformations of the question. | CS.arxiv | 2020-02-19 |
| 180 | Neural Relation Prediction for Simple Question Answering over Knowledge Graph | AMIN ABOLGHASEMI et. al. | In this paper, we propose an instance-based method to find similar questions of a new question, in the sense of their relations, to predict its mentioned relation. | CS.arxiv | 2020-02-18 |
| 181 | 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 |
| 182 | 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 |
| 183 | Text-based Question Answering from Information Retrieval and Deep Neural Network Perspectives: A Survey | ZAHRA ABBASIYANTAEB 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 |
| 184 | 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 |
| 185 | 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 |
| 186 | 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 |
| 187 | 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.arxiv | 2020-02-13 |
| 188 | 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 |
| 189 | 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 |
| 190 | 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.arxiv | 2020-02-09 |
| 191 | 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 |
| 192 | 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 |
| 193 | Translating Web Search Queries into Natural Language Questions | ADARSH KUMAR et. al. | In this paper, we are proposing a method to generate well-formed natural language question from a given keyword-based query, which has the same question intent as the query. | CS.arxiv | 2020-02-07 |
| 194 | Generating Scientific Question Answering Corpora from Q&A forums | ANDRE LAMURIAS et. al. | We present a method to automatically extract question-article pairs from Q&A web forums, which can be used for document retrieval and QA tasks. We generated the SciQA corpus by applying our framework to three forums, obtaining 5,432 questions and 10,208 question-article pairs. | CS.arxiv | 2020-02-06 |
| 195 | K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters | RUIZE WANG et. al. | To address this, we propose K-Adapter, which remains the original parameters of the pre-trained model fixed and supports continual knowledge infusion. | CS.arxiv | 2020-02-05 |
| 196 | Quality Assurance Technologies of Big Data Applications: A Systematic Literature Review | PENGCHENG ZHANG et. al. | This paper aims at summarizing and assessing existing quality assurance (QA) technologies addressing quality issues in big data applications. | CS.arxiv | 2020-02-05 |
| 197 | UNCC Biomedical Semantic Question Answering Systems. BioASQ: Task-7B, Phase-B | SAI KRISHNA TELUKUNTLA et. al. | In this paper, we detail our submission to the 2019, 7th year, BioASQ competition. | CS.arxiv | 2020-02-05 |
| 198 | Web Table Extraction, Retrieval and Augmentation: A Survey | SHUO ZHANG et. al. | The objective of this survey is to synthesize and present two decades of research on web tables. | CS.arxiv | 2020-02-01 |
| 199 | Augmenting Visual Question Answering with Semantic Frame Information in a Multitask Learning Approach | MEHRDAD ALIZADEH et. al. | Several deep neural network approaches have been proposed to model the task in an end-to-end fashion. | CS.arxiv | 2020-01-31 |
| 200 | Break It Down: A Question Understanding Benchmark | TOMER WOLFSON et. al. | In this work, we introduce a Question Decomposition Meaning Representation (QDMR) for questions. | CS.arxiv | 2020-01-31 |
| 201 | Pretrained Transformers for Simple Question Answering over Knowledge Graphs | D. LUKOVNIKOV et. al. | In this work, we investigate how well BERT performs on SimpleQuestions and provide an evaluation of both BERT and BiLSTM-based models in datasparse scenarios. | CS.arxiv | 2020-01-31 |
| 202 | Teaching Machines to Converse | JIWEI LI | This dissertation attempts to tackle these challenges: Contributions are two-fold: (1) we address new challenges presented by neural network models in open-domain dialogue generation systems; (2) we develop interactive question-answering dialogue systems by (a) giving the agent the ability to ask questions and (b) training a conversation agent through interactions with humans in an online fashion, where a bot improves through communicating with humans and learning from the mistakes that it makes. | CS.arxiv | 2020-01-31 |
| 203 | Data Mining in Clinical Trial Text: Transformers for Classification and Question Answering Tasks | LENA SCHMIDT et. al. | All models in this paper were created with the aim to support systematic review (semi)automation. | CS.arxiv | 2020-01-30 |
| 204 | MEMO: A Deep Network for Flexible Combination of Episodic Memories | ANDREA BANINO et. al. | Recent research developing neural network architectures with external memory have often used the benchmark bAbI question and answering dataset which provides a challenging number of tasks requiring reasoning. | CS.arxiv | 2020-01-29 |
| 205 | The KEEN Universe: An Ecosystem for Knowledge Graph Embeddings with a Focus on Reproducibility and Transferability | MEHDI ALI et. al. | Therefore, we present the KEEN Universe, an ecosystem for knowledge graph embeddings that we have developed with a strong focus on reproducibility and transferability. | CS.arxiv | 2020-01-28 |
| 206 | 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.arxiv | 2020-01-27 |
| 207 | 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.arxiv | 2020-01-25 |
| 208 | Intent Classification in Question-Answering Using LSTM Architectures | GIOVANNI DI GENNARO et. al. | Through the use of an LSTM network, we show how this type of classification can be approached effectively and efficiently, and how it can be properly used within a basic prototype responder. | CS.arxiv | 2020-01-25 |
| 209 | Robust Explanations for Visual Question Answering | BADRI N. PATRO et. al. | In this paper, we propose a method to obtain robust explanations for visual question answering(VQA) that correlate well with the answers. | CS.arxiv | 2020-01-23 |
| 210 | 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.arxiv | 2020-01-22 |
| 211 | Accuracy vs. Complexity: A Trade-off in Visual Question Answering Models | MOSHIUR R. FARAZI et. al. | In this work, we systematically study the trade-off between the model complexity and the performance on the VQA task. | CS.arxiv | 2020-01-20 |
| 212 | 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.arxiv | 2020-01-20 |
| 213 | Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features | ANDRES MAFLA et. al. | In this paper, we address the problem of fine-grained classification and image retrieval by leveraging textual information along with visual cues to comprehend the existing intrinsic relation between the two modalities. | CS.arxiv | 2020-01-14 |
| 214 | Negative Statements Considered Useful | HIBA ARNAOUT et. al. | We introduce two approaches towards compiling negative statements. | CS.arxiv | 2020-01-13 |
| 215 | MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding | GEONDO PARK et. al. | Thus, in addition to the joint embedding space, we propose a novel multi-head self-attention network to capture various components of visual and textual data by attending to important parts in data. | CS.arxiv | 2020-01-11 |
| 216 | 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.arxiv | 2020-01-10 |
| 217 | Machine Learning Approaches for Amharic Parts-of-speech Tagging | IBRAHIM GASHAW et. al. | The aim of this work is to improve POS tagging performance for the Amharic language, which was never above 91%. | CS.arxiv | 2020-01-10 |
| 218 | Visual Question Answering on 360� Images | SHIH-HAN CHOU et. al. | In this work, we introduce VQA 360, a novel task of visual question answering on 360 images. To address this problem, we collect the first VQA 360 dataset, containing around 17,000 real-world image-question-answer triplets for a variety of question types. | CS.arxiv | 2020-01-10 |
| 219 | Open Domain Question Answering Using Web Tables | KAUSHIK CHAKRABARTI et. al. | In this paper, we develop an open-domain QA approach using web tables that works for both factoid and non-factoid queries. | CS.arxiv | 2020-01-09 |
| 220 | Managing Device Lifecycle: Reconfigurable Constrained Codes for M/T/Q/P-LC Flash Memories | AHMED HAREEDY et. al. | Recently, we introduced binary symmetric lexicographically-ordered constrained codes (LOCO codes) for data storage and data transmission. | CS.arxiv | 2020-01-07 |
| 221 | Multi-Layer Content Interaction Through Quaternion Product For Visual Question Answering | LEI SHI et. al. | Extensive ablation study has been carried out to testify the influence of each proposed module in this study. | CS.arxiv | 2020-01-02 |
| 222 | Side-Tuning: Network Adaptation via Additive Side Networks | JEFFREY O ZHANG et. al. | In this paper, we propose a straightforward alternative: Side-Tuning. | CS.arxiv | 2019-12-31 |
| 223 | What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge | KYLE RICHARDSON et. al. | To investigate this, we introduce several new challenge tasks that probe whether state-of-the-art QA models have general knowledge about word definitions and general taxonomic reasoning, both of which are fundamental to more complex forms of reasoning and are widespread in benchmark datasets. | CS.arxiv | 2019-12-31 |
| 224 | Complex Program Induction for Querying Knowledge Bases in the Absence of Gold Programs | AMRITA SAHA et. al. | We present Complex Imperative Program Induction from Terminal Rewards (CIPITR), an advanced neural programmer that mitigates reward sparsity with auxiliary rewards, and restricts the program space to semantically correct programs using high-level constraints, KB schema, and inferred answer type. | CS.tacl | 2019-12-30 |
| 225 | CoQA: A Conversational Question Answering Challenge | SIVA REDDY et. al. | We introduce CoQA, a novel dataset for building Conversational Question Answering systems. | CS.tacl | 2019-12-30 |
| 226 | Natural Questions: A Benchmark for Question Answering Research | TOM KWIATKOWSKI et. al. | We present the Natural Questions corpus, a question answering data set. | CS.tacl | 2019-12-30 |
| 227 | The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries | ATEF CHAUDHURY et. al. | In this paper, we introduce the Shmoop Corpus: a dataset of 231 stories that are paired with detailed multi-paragraph summaries for each individual chapter (7,234 chapters), where the summary is chronologically aligned with respect to the story chapter. From the corpus, we construct a set of common NLP tasks, including Cloze-form question answering and a simplified form of abstractive summarization, as benchmarks for reading comprehension on stories. | CS.arxiv | 2019-12-30 |
| 228 | Trick Me If You Can: Human-in-the-Loop Generation of Adversarial Examples for Question Answering | ERIC WALLACE et. al. | We propose human- in-the-loop adversarial generation, where human authors are guided to break models. | CS.tacl | 2019-12-30 |
| 229 | Vision and Language: from Visual Perception to Content Creation | TAO MEI et. al. | This paper reviews the recent advances along these two dimensions: vision to language and language to vision. | CS.arxiv | 2019-12-26 |
| 230 | Learning to Answer Ambiguous Questions with Knowledge Graph | YIKAI ZHU et. al. | In this paper, we present a new way to utilize the dataset that takes into account the existence of ambiguous questions. | CS.arxiv | 2019-12-25 |
| 231 | Abductive Commonsense Reasoning | CHANDRA BHAGAVATULA et. al. | We present the first study that investigates the viability of language-based abductive reasoning. We introduce a challenge dataset, ART, that consists of over 20k commonsense narrative contexts and 200k explanations. | CS.iclr | 2019-12-21 |
| 232 | AdvCodec: Towards A Unified Framework for Adversarial Text Generation | BOXIN WANG et. al. | The main contribution of this paper is to propose a general targeted attack framework AdvCodec for adversarial text generation which addresses the challenge of discrete input space and is easily adapted to general natural language processing (NLP) tasks. | CS.arxiv | 2019-12-21 |
| 233 | Efficient Transformer for Mobile Applications | ZHANGHAO WU* et. al. | In this paper, we investigate the mobile setting (under 500M Mult-Adds) for NLP tasks to facilitate the deployment on the edge devices. | CS.iclr | 2019-12-21 |
| 234 | Learning from Explanations with Neural Module Execution Tree | YUJIA QIN et. al. | In this paper, we propose a novel Neural Modular Execution Tree (NMET) framework for augmenting sequence classification with NL explanations. | CS.iclr | 2019-12-21 |
| 235 | Measuring Compositional Generalization: A Comprehensive Method on Realistic Data | DANIEL KEYSERS et. al. | Benchmark and method to measure compositional generalization by maximizing divergence of compound frequency at small divergence of atom frequency. | CS.iclr | 2019-12-21 |
| 236 | MEMO: A Deep Network for Flexible Combination of Episodic Memories | ANDREA BANINO et. al. | A memory architecture that support inferential reasoning. | CS.iclr | 2019-12-21 |
| 237 | NeurQuRI: Neural Question Requirement Inspector for Answerability Prediction in Machine Reading Comprehension | SEOHYUN BACK et. al. | We propose a neural question requirement inspection model called NeurQuRI that extracts a list of conditions from the question, each of which should be satisfied by the candidate answer generated by an MRC model. | CS.iclr | 2019-12-21 |
| 238 | Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model | WENHAN XIONG et. al. | In this work, we further investigate the extent to which pretrained models such as BERT capture knowledge using a zero-shot fact completion task. | CS.iclr | 2019-12-21 |
| 239 | Reducing Transformer Depth on Demand with Structured Dropout | ANGELA FAN et. al. | Layerdrop, a form of structured dropout that allows you to train one model at training time and prune to any desired depth at test time. You can also | CS.iclr | 2019-12-21 |
| 240 | StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding | WEI WANG et. al. | Inspired by the linearization exploration work of Elman, we extend BERT to a new model, StructBERT, by incorporating language structures into pre-training. | CS.iclr | 2019-12-21 |
| 241 | Transformer-XH: Multi-hop question answering with eXtra Hop attention | CHEN ZHAO et. al. | We present Transformer-XH, which upgrades Transformer with eXtra Hop attentions to intrinsically model structured texts in a data driven way. It leads to a simpler yet state-of-the-art multi-hop QA system. | CS.iclr | 2019-12-21 |
| 242 | Measuring Compositional Generalization: A Comprehensive Method on Realistic Data | DANIEL KEYSERS et. al. | We introduce a novel method to systematically construct such benchmarks by maximizing compound divergence while guaranteeing a small atom divergence between train and test sets, and we quantitatively compare this method to other approaches for creating compositional generalization benchmarks. | CS.arxiv | 2019-12-20 |
| 243 | Deep Exemplar Networks for VQA and VQG | BADRI N. PATRO et. al. | In this paper, we consider the problem of solving semantic tasks such as `Visual Question Answering’ (VQA), where one aims to answers related to an image and `Visual Question Generation’ (VQG), where one aims to generate a natural question pertaining to an image. | CS.arxiv | 2019-12-19 |
| 244 | 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.arxiv | 2019-12-18 |
| 245 | Knowledge-Enhanced Attentive Learning for Answer Selection in Community Question Answering Systems | FENGSHI JING et. al. | We propose the Knowledge-enhanced Attentive Answer Selection (KAAS) model, which enhances the performance through (a) considering both the expertise and the authority of the answerer; (b) utilizing the human-labeled tags, the taxonomy of the tags, and the votes as the domain knowledge to infer the expertise of the answer; (c) using matrix decomposition of the social network (formed by following-relationship) to infer the authority of the answerer and incorporating such information in the process of evaluating the similarity between segments. | CS.arxiv | 2019-12-17 |
| 246 | Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering | JIAN WANG et. al. | In this paper, we propose a novel knowledge-aware dialogue generation model (called TransDG), which transfers question representation and knowledge matching abilities from knowledge base question answering (KBQA) task to facilitate the utterance understanding and factual knowledge selection for dialogue generation. | CS.arxiv | 2019-12-16 |
| 247 | Pipelines for Procedural Information Extraction from Scientific Literature: Towards Recipes using Machine Learning and Data Science | HUICHEN YANG et. al. | This paper describes a machine learning and data science pipeline for structured information extraction from documents, implemented as a suite of open-source tools and extensions to existing tools. | CS.arxiv | 2019-12-16 |
| 248 | 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.arxiv | 2019-12-16 |
| 249 | Knowledge-based Conversational Search | SVITLANA VAKULENKO | In this thesis, we lay foundations for designing conversational search systems by analyzing the requirements and proposing concrete solutions for automating some of the basic components and tasks that such systems should support. | CS.arxiv | 2019-12-14 |
| 250 | Context-aware Entity Linking with Attentive Neural Networks on Wikidata Knowledge Graph | ISAIAH ONANDO MULANG et. al. | In this paper, we advance the state-of-the-art approaches by developing a context-aware attentive neural network approach for entity linking on Wikidata. | CS.arxiv | 2019-12-12 |
| 251 | AliMe KBQA: Question Answering over Structured Knowledge for E-commerce Customer Service | FENG-LIN LI et. al. | In this paper, we present AliMe-KBQA, a bold attempt to apply KBQA in the E-commerce customer service field. | CS.arxiv | 2019-12-11 |
| 252 | Automatic Spanish Translation of the SQuAD Dataset for Multilingual Question Answering | CASIMIRO PIO CARRINO et. al. | In this work, we develop the Translate Align Retrieve (TAR) method to automatically translate the Stanford Question Answering Dataset (SQuAD) v1.1 to Spanish. | CS.arxiv | 2019-12-11 |
| 253 | Efficient crowdsourcing of crowd-generated microtasks | ABIGAIL HOTALING et. al. | In this paper, we introduce *cost forecasting* as a means for a crowdsourcer to use efficient crowdsourcing algorithms with a growing set of microtasks. | CS.arxiv | 2019-12-10 |
| 254 | Medication Regimen Extraction From Medical Conversations | SAI P. SELVARAJ et. al. | In this paper, we focus on extracting the Medication Regimen (dosage and frequency for medications) discussed in a medical conversation. | CS.arxiv | 2019-12-10 |
| 255 | Neural Module Networks for Reasoning over Text | NITISH GUPTA et. al. | We extend NMNs by: (a) introducing modules that reason over a paragraph of text, performing symbolic reasoning (such as arithmetic, sorting, counting) over numbers and dates in a probabilistic and differentiable manner; and (b) proposing an unsupervised auxiliary loss to help extract arguments associated with the events in text. | CS.arxiv | 2019-12-10 |
| 256 | AI2D-RST: A multimodal corpus of 1000 primary school science diagrams | TUOMO HIIPPALA et. al. | This article introduces AI2D-RST, a multimodal corpus of 1000 English-language diagrams that represent topics in primary school natural sciences, such as food webs, life cycles, moon phases and human physiology. | CS.arxiv | 2019-12-09 |
| 257 | Exploring the Ideal Depth of Neural Network when Predicting Question Deletion on Community Question Answering | SOUVICK GHOSH et. al. | In this paper, we have explored how the depth of the neural network influences the accuracy of prediction of deleted questions in question-answering forums. | CS.arxiv | 2019-12-07 |
| 258 | Machine Translation Evaluation Meets Community Question Answering | FRANCISCO GUZM�N et. al. | We explore the applicability of machine translation evaluation (MTE) methods to a very different problem: answer ranking in community Question Answering. | CS.arxiv | 2019-12-06 |
| 259 | Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks | CORENTIN KERVADEC et. al. | In this paper we claim that these State-Of-The-Art (SOTA) approaches perform reasonably well in structuring information inside a single modality but, despite their impressive performances , they tend to struggle to identify fine-grained inter-modality relationships. | CS.arxiv | 2019-12-06 |
| 260 | 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 training regime. | CS.arxiv | 2019-12-04 |
| 261 | An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering | SHAYNE LONGPRE et. al. | We find a simple negative sampling technique to be particularly effective, even though it is typically used for datasets that include unanswerable questions, such as SQuAD 2.0. | CS.arxiv | 2019-12-04 |
| 262 | Cooperative Reasoning on Knowledge Graph and Corpus: A Multi-agentReinforcement Learning Approach | YUNAN ZHANG et. al. | In this paper, we propose a model that leverages the text corpus to cure such limitations, either the explicit or implicit missing links. | CS.arxiv | 2019-12-04 |
| 263 | 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.arxiv | 2019-12-04 |
| 264 | Deep Bayesian Active Learning for Multiple Correct Outputs | KHALED JEDOUI et. al. | In this paper, we propose a new paradigm that estimates uncertainty in the model’s internal hidden space instead of the model’s output space. | CS.arxiv | 2019-12-02 |
| 265 | TutorialVQA: Question Answering Dataset for Tutorial Videos | ANTHONY COLAS et. al. | To adequately address this, We propose a new question answering task on instructional videos, because of their verbose and narrative nature. | CS.arxiv | 2019-12-02 |
| 266 | Unsupervised Inflection Generation Using Neural Language Modeling | OCTAVIA-MARIA SULEA et. al. | In this paper we investigate the extent to which these new unsupervised or generative techniques can serve to alleviate the type-token ratio disparity in morphologically rich languages. | CS.arxiv | 2019-12-02 |
| 267 | A Hybrid Approach Towards Two Stage Bengali Question Classification Utilizing Smart Data Balancing Technique | MD. HASIBUR RAHMAN et. al. | We present a two stage QC system for Bengali. | CS.arxiv | 2019-11-29 |
| 268 | An Iterative Polishing Framework based on Quality Aware Masked Language Model for Chinese Poetry Generation | LIMING DENG et. al. | In this paper, we propose a novel iterative polishing framework for highly qualified Chinese poetry generation. | CS.arxiv | 2019-11-29 |
| 269 | 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.arxiv | 2019-11-27 |
| 270 | A Vietnamese Text-Based Conversational Agent | DAI QUOC NGUYEN et. al. | This paper introduces a Vietnamese text-based conversational agent architecture on specific knowledge domain which is integrated in a question answering system. | CS.arxiv | 2019-11-26 |
| 271 | 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.arxiv | 2019-11-26 |
| 272 | Label Dependent Deep Variational Paraphrase Generation | SIAMAK SHAKERI et. al. | In this article, we propose a deep variational model to generate paraphrases conditioned on a label that specifies whether the paraphrases are semantically related or not. | CS.arxiv | 2019-11-26 |
| 273 | 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.arxiv | 2019-11-26 |
| 274 | SemEval-2015 Task 3: Answer Selection in Community Question Answering | PRESLAV NAKOV et. al. | We set subtask A for Arabic and English on two relatively different cQA domains, i.e., the Qatar Living website for English, and a Quran-related website for Arabic. | CS.arxiv | 2019-11-26 |
| 275 | Transfer Learning in Visual and Relational Reasoning | T. S. JAYRAM et. al. | In this work, we formalize these unique aspects of transfer learning and propose a theoretical framework for visual reasoning, exemplified by the well-established CLEVR and COG datasets. | CS.arxiv | 2019-11-26 |
| 276 | Unsupervised Domain Adaptation of Language Models for Reading Comprehension | KOSUKE NISHIDA et. al. | To solve the UDARC problem, we provide two domain adaptation models. | CS.arxiv | 2019-11-25 |
| 277 | Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering | AKARI ASAI et. al. | This paper introduces a new graph-based recurrent retrieval approach that learns to retrieve reasoning paths over the Wikipedia graph to answer multi-hop open-domain questions. | CS.arxiv | 2019-11-24 |
| 278 | ScienceExamCER: A High-Density Fine-Grained Science-Domain Corpus for Common Entity Recognition | HANNAH SMITH et. al. | In this work we present ScienceExamCER, a densely-labeled semantic classification corpus of 133k mentions in the science exam domain where nearly all (96%) of content words have been annotated with one or more fine-grained semantic class labels including taxonomic groups, meronym groups, verb/action groups, properties and values, and synonyms. | CS.arxiv | 2019-11-23 |
| 279 | Unsupervised Keyword Extraction for Full-sentence VQA | KOHEI UEHARA et. al. | In this study, we envision a new VQA task in natural situations, where the answers would more likely to be sentences, rather than single words. | CS.arxiv | 2019-11-23 |
| 280 | Interactive Text Ranking with Bayesian Optimisation: A Case Study on Community QA and Summarisation | EDWIN SIMPSON et. al. | To address the lack of user-specific training data, we propose an interactive text ranking approach that actively selects pairs of candidates, from which the user selects the best. | CS.arxiv | 2019-11-22 |
| 281 | The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service | MENG CHEN et. al. | In this paper, we construct a large-scale real scenario Chinese E-commerce conversation corpus, JDDC, with more than 1 million multi-turn dialogues, 20 million utterances, and 150 million words. | CS.arxiv | 2019-11-22 |
| 282 | Improving Conditioning in Context-Aware Sequence to Sequence Models | XINYI WANG et. al. | In this work, we focus on cases where generation is conditioned on both a short query and a long context, such as abstractive question answering or document-level translation. | CS.arxiv | 2019-11-21 |
| 283 | 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.arxiv | 2019-11-21 |
| 284 | Paraphrasing with Large Language Models | SAM WITTEVEEN et. al. | We present a useful technique for using a large language model to perform the task of paraphrasing on a variety of texts and subjects. | CS.arxiv | 2019-11-21 |
| 285 | Temporal Reasoning via Audio Question Answering | HAYTHAM M. FAYEK et. al. | In this paper, we use the task of Audio Question Answering (AQA) to study the temporal reasoning abilities of machine learning models. | CS.arxiv | 2019-11-21 |
| 286 | What Do You Mean `Why?’: Resolving Sluices in Conversations | VICTOR PETR�N 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.arxiv | 2019-11-21 |
| 287 | Global Thread-Level Inference for Comment Classification in Community Question Answering | SHAFIQ JOTY et. al. | More specifically, we exploit the relations between pairs of comments at any distance in the thread, which we incorporate in a graph-cut and in an ILP frameworks. | CS.arxiv | 2019-11-20 |
| 288 | SemanticZ at SemEval-2016 Task 3: Ranking Relevant Answers in Community Question Answering Using Semantic Similarity Based on Fine-tuned Word Embeddings | TODOR MIHAYLOV et. al. | We describe our system for finding good answers in a community forum, as defined in SemEval-2016, Task 3 on Community Question Answering. | CS.arxiv | 2019-11-20 |
| 289 | Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA | BADRI N. PATRO et. al. | In this paper, we aim to obtain improved attention for a visual question answering (VQA) task. | CS.arxiv | 2019-11-19 |
| 290 | Unsupervised Natural Question Answering with a Small Model | MARTIN ANDREWS et. al. | The contribution of this work is that the methods presented here rely on unsupervised learning techniques, complementing the unsupervised training of the Language Model. | CS.arxiv | 2019-11-19 |
| 291 | 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.arxiv | 2019-11-17 |
| 292 | Multi-task Sentence Encoding Model for Semantic Retrieval in Question Answering Systems | QIANG HUANG et. al. | In this paper, we propose a Multi-task Sentence Encoding Model (MSEM) for the PI problem, wherein a connected graph is employed to depict the relation between sentences, and a multi-task learning model is applied to address both the sentence matching and sentence intent classification problem. | CS.arxiv | 2019-11-17 |
| 293 | Quick and (not so) Dirty: Unsupervised Selection of Justification Sentences for Multi-hop Question Answering | VIKAS YADAV et. al. | We propose an unsupervised strategy for the selection of justification sentences for multi-hop question answering (QA) that (a) maximizes the relevance of the selected sentences, (b) minimizes the overlap between the selected facts, and (c) maximizes the coverage of both question and answer. | CS.arxiv | 2019-11-17 |
| 294 | Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations | FENGLIN LIU et. al. | In this work, we aim at representing an image with a set of integrated visual regions and corresponding textual concepts, reflecting certain semantics. | CS.nips | 2019-11-15 |
| 295 | Compositional De-Attention Networks | YI TAY et. al. | This paper proposes a new quasi-attention that is compositional in nature, i.e., learning whether to \textit{add}, \textit{subtract} or \textit{nullify} a certain vector when learning representations. | CS.nips | 2019-11-15 |
| 296 | Neural Shuffle-Exchange Networks – Sequence Processing in O(n log n) Time | KARLIS FREIVALDS et. al. | We introduce a new Shuffle-Exchange neural network model for sequence to sequence tasks which have O(log n) depth and O(n log n) total complexity. | CS.nips | 2019-11-15 |
| 298 | RUBi: Reducing Unimodal Biases for Visual Question Answering | REMI CADENE et. al. | We propose RUBi, a new learning strategy to reduce biases in any VQA model. | CS.nips | 2019-11-15 |
| 299 | Self-Critical Reasoning for Robust Visual Question Answering | JIALIN WU et. al. | To address this issue, we introduce a self-critical training objective that ensures that visual explanations of correct answers match the most influential image regions more than other competitive answer candidates. | CS.nips | 2019-11-15 |
| 300 | TAB-VCR: Tags and Attributes based VCR Baselines | JINGXIANG LIN et. al. | Here we show that a much simpler model obtained by ablating and pruning the existing intricate baseline can perform better with half the number of trainable parameters. | CS.nips | 2019-11-15 |
| 301 | Towards Interpretable Reinforcement Learning Using Attention Augmented Agents | ALEXANDER MOTT et. al. | Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. | CS.nips | 2019-11-15 |
| 302 | Unified Language Model Pre-training for Natural Language Understanding and Generation | LI DONG et. al. | This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. | CS.nips | 2019-11-15 |
| 303 | ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks | JIASEN LU et. al. | We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. | CS.nips | 2019-11-15 |
| 304 | XLNet: Generalized Autoregressive Pretraining for Language Understanding | ZHILIN YANG et. al. | In light of these pros and cons, we propose XLNet, a generalized autoregressive pretraining method that (1) enables learning bidirectional contexts by maximizing the expected likelihood over all permutations of the factorization order and (2) overcomes the limitations of BERT thanks to its autoregressive formulation. | CS.nips | 2019-11-15 |
| 305 | Question-Conditioned Counterfactual Image Generation for VQA | JINGJING PAN et. al. | In this ongoing work, we propose addressing this shortcoming by learning to generate counterfactual images for a VQA model – i.e. given a question-image pair, we wish to generate a new image such that i) the VQA model outputs a different answer, ii) the new image is minimally different from the original, and iii) the new image is realistic. | CS.arxiv | 2019-11-14 |
| 306 | Adapting and evaluating a deep learning language model for clinical why-question answering | ANDREW WEN et. al. | Objectives: To adapt and evaluate a deep learning language model for answering why-questions based on patient-specific clinical text. | CS.arxiv | 2019-11-13 |
| 307 | FAQ-based Question Answering via Knowledge Anchors | RUOBING XIE et. al. | In this paper, we propose a novel Knowledge Anchor based Question Answering (KAQA) framework for FAQ-based QA to better understand questions and retrieve more appropriate answers. | CS.arxiv | 2019-11-13 |
| 308 | Neural Duplicate Question Detection without Labeled Training Data | ANDREAS R�CKL� et. al. | In this work, we propose two novel methods—weak supervision using the title and body of a question, and the automatic generation of duplicate questions—and show that both can achieve improved performances even though they do not require any labeled data. | CS.arxiv | 2019-11-13 |
| 309 | A Survey on Why-Type Question Answering Systems | MANVI BREJA et. al. | The paper presents a survey on Why-type Question Answering System, details the architecture, the processes involved in the system and suggests further areas of research. | CS.arxiv | 2019-11-12 |
| 310 | EDUQA: Educational Domain Question Answering System using Conceptual Network Mapping | ABHISHEK AGARWAL et. al. | In this paper, we propose an on-the-fly conceptual network model that incorporates educational semantics. | CS.arxiv | 2019-11-12 |
| 311 | Meta Answering for Machine Reading | BENJAMIN BORSCHINGER et. al. | We investigate a framework for machine reading, inspired by real world information-seeking problems, where a meta question answering system interacts with a black box environment. | CS.arxiv | 2019-11-11 |
| 312 | TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection | SIDDHANT GARG et. al. | We propose TANDA, an effective technique for fine-tuning pre-trained Transformer models for natural language tasks. We built a large scale dataset to enable the transfer step, exploiting the Natural Questions dataset. | CS.arxiv | 2019-11-11 |
| 313 | Dynamic Knowledge Graph Construction for Zero-shot Commonsense Question Answering | ANTOINE BOSSELUT et. al. | In this paper, we present initial studies toward zero-shot commonsense QA by formulating the task as probabilistic inference over dynamically generated commonsense knowledge graphs. | CS.arxiv | 2019-11-10 |
| 314 | Knowledge Guided Named Entity Recognition for BioMedical Text | PRATYAY BANERJEE et. al. | In this work, we formulate the NER task as a multi-answer question answering (MAQA) task and provide different knowledge contexts, such as entity types, questions, definitions and definitions with examples. | CS.arxiv | 2019-11-10 |
| 315 | Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering | SEWON MIN et. al. | We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge base or co-occurrence in the same article. | CS.arxiv | 2019-11-10 |
| 316 | Learning to Order Sub-questions for Complex Question Answering | YUNAN ZHANG et. al. | In this paper, we propose a novel reinforcement learning(RL) approach to answering complex questions that can learn a policy to dynamically decide which sub-question should be answered at each stage of reasoning. | CS.arxiv | 2019-11-10 |
| 317 | Multimodal Intelligence: Representation Learning, Information Fusion, and Applications | CHAO ZHANG et. al. | In this paper, we provide a technical review of available models and learning methods for multimodal intelligence. | CS.arxiv | 2019-11-10 |
| 318 | Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation | YIMING XU et. al. | In this paper, we tackle the above issues by proposing a novel supervised multi-modal domain adaptation method for VQA to learn joint feature embeddings across different domains and modalities. | CS.arxiv | 2019-11-10 |
| 319 | E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT | NINA POERNER et. al. | We present a novel way of injecting factual knowledge about entities into the pretrained BERT model (Devlin et al., 2019): We align Wikipedia2Vec entity vectors (Yamada et al., 2016) with BERT’s native wordpiece vector space and use the aligned entity vectors as if they were wordpiece vectors. | CS.arxiv | 2019-11-09 |
| 320 | Hierarchical Graph Network for Multi-hop Question Answering | YUWEI FANG et. al. | In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. | CS.arxiv | 2019-11-09 |
| 321 | A Comprehensive Comparison of Machine Learning Based Methods Used in Bengali Question Classification | AFRA ANIKA et. al. | We present a comprehensive comparison (performance and computational complexity) among some machine learning based approaches used in QC for Bengali language. | CS.arxiv | 2019-11-08 |
| 322 | Are we asking the right questions in MovieQA? | BHAVAN JASANI et. al. | In this paper, we explore the biases in the MovieQA dataset and propose a strikingly simple model which can exploit them. | CS.arxiv | 2019-11-08 |
| 323 | Ask to Learn: A Study on Curiosity-driven Question Generation | THOMAS SCIALOM et. al. | We propose a novel text generation task, namely Curiosity-driven Question Generation. | CS.arxiv | 2019-11-08 |
| 324 | Crowdsourcing a High-Quality Gold Standard for QA-SRL | PAUL ROIT et. al. | In this paper, we present an improved QA-SRL annotation protocol, involving crowd-worker selection and training, followed by data consolidation. Applying this process, we release a new gold evaluation dataset for QA-SRL, yielding more consistent annotations and greater coverage. | CS.arxiv | 2019-11-08 |
| 325 | Discovering Relevant Reviews for Answering Product-Related Queries | S. ZHANG et. al. | To address this, we propose two neural models that discover relevant reviews for answering product queries. | CS.icdm | 2019-11-08 |
| 326 | Fast LSTM Inference by Dynamic Decomposition on Cloud Systems | Y. YOU ET AL. | In this paper we aim to minimize the latency of LSTM inference on cloud systems without losing accuracy. | CS.icdm | 2019-11-08 |
| 327 | Multi-hop Knowledge Base Question Answering with an Iterative Sequence Matching Model | Y. LAN et. al. | In this paper, we propose a novel iterative sequence matching model to address several limitations of previous methods for multi-hop KBQA. | CS.icdm | 2019-11-08 |
| 328 | Negated LAMA: Birds cannot fly | NORA KASSNER et. al. | Pretrained language models have achieved remarkable improvements in a broad range of natural language processing tasks, including question answering (QA). | CS.arxiv | 2019-11-08 |
| 329 | Preference Relationship-Based CrossCMN Scheme for Answer Ranking in Community QA | Q. CHEN et. al. | To improve such problem, we design a novel scheme, named PW-CrossCMN. The scheme ranks the candidate answers by pair-wise approach based on numerous historical documents. | CS.icdm | 2019-11-08 |
| 330 | Blockwise Self-Attention for Long Document Understanding | JIEZHONG QIU et. al. | We present BlockBERT, a lightweight and efficient BERT model that is designed to better modeling long-distance dependencies. | CS.arxiv | 2019-11-07 |
| 331 | 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.arxiv | 2019-11-07 |
| 332 | The TechQA Dataset | VITTORIO CASTELLI et. al. | We introduce TechQA, a domain-adaptation question answering dataset for the technical support domain. | CS.arxiv | 2019-11-07 |
| 333 | Why Do Masked Neural Language Models Still Need Common Sense Knowledge? | SUNJAE KWON et. al. | This paper provides empirical but insightful analyses on the pretrained MNLMs with respect to common sense knowledge. | CS.arxiv | 2019-11-07 |
| 334 | A Spoken Dialogue System for Spatial Question Answering in a Physical Blocks World | GEORGIY PLATONOV et. al. | In this work we tackle spatial question answering in a holistic way, using a vision system, speech input and output mediated by an animated avatar, a dialogue system that robustly interprets spatial queries, and a constraint solver that derives answers based on 3-D spatial modeling. | CS.arxiv | 2019-11-06 |
| 335 | Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds | TASSILO KLEIN et. al. | In this work, we propose a variant of the self-attention Transformer network architectures model to generate meaningful and diverse questions. | CS.arxiv | 2019-11-06 |
| 336 | Towards Domain Adaptation from Limited Data for Question Answering Using Deep Neural Networks | TIMOTHY J. HAZEN et. al. | This paper explores domain adaptation for enabling question answering (QA) systems to answer questions posed against documents in new specialized domains. | CS.arxiv | 2019-11-06 |
| 337 | Unsupervised Domain Adaptation of Contextual Embeddings for Low-Resource Duplicate Question Detection | ALEXANDRE ROCHETTE et. al. | In this paper, we apply BERT to DQD and advance it by unsupervised adaptation to StackExchange domains using self-supervised learning. | CS.arxiv | 2019-11-06 |
| 338 | Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network | DEMING YE et. al. | In this work, we propose a knowledge-enhanced graph neural network (KGNN), which performs reasoning over multiple paragraphs with entities. | CS.arxiv | 2019-11-05 |
| 339 | BAS: An Answer Selection Method Using BERT Language Model | JAMSHID MOZAFARI et. al. | In this research, we will present the BAS (BERT Answer Selection) that uses the BERT language model to comprehend language. | CS.arxiv | 2019-11-04 |
| 340 | Learning from Explanations with Neural Execution Tree | ZIQI WANG et. al. | In this paper, we propose a novel Neural Execution Tree (NExT) framework to augment training data for text classification using NL explanations. | CS.arxiv | 2019-11-04 |
| 341 | A Compare-Aggregate Model with Latent Clustering for Answer Selection | SEUNGHYUN YOON et. al. | In this paper, we propose a novel method for a sentence-level answer-selection task that is a fundamental problem in natural language processing. | CS.cikm | 2019-11-03 |
| 342 | Adapting Visual Question Answering Models for Enhancing Multimodal Community Q&A Platforms | AVIKALP SRIVASTAVA et. al. | With the increasingly multimodal nature of web content, we focus on extending these methods for CQA questions accompanied by images. | CS.cikm | 2019-11-03 |
| 343 | An Interactive Mechanism to Improve Question Answering Systems via Feedback | XINBO ZHANG et. al. | To provide better interactivity and online performance, we design a holistic graph mining algorithm (HWspan) to automatically refine the query graph. | CS.cikm | 2019-11-03 |
| 344 | Attentive History Selection for Conversational Question Answering | CHEN QU et. al. | In this work, we propose a novel solution for ConvQA that involves three aspects. | CS.cikm | 2019-11-03 |
| 345 | Commonsense Properties from Query Logs and Question Answering Forums | JULIEN ROMERO et. al. | This paper presents Quasimodo, a methodology and tool suite for distilling commonsense properties from non-standard web sources. | CS.cikm | 2019-11-03 |
| 346 | Constrained Co-embedding Model for User Profiling in Question Answering Communities | YUPENG LUO et. al. | In this paper, we study the problem of user profiling in question answering communities. | CS.cikm | 2019-11-03 |
| 347 | Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System | YE LIU et. al. | In order to eliminate the effect of ill-formed questions, we approach the question refinement task and propose a unified model, QREFINE, to refine the ill-formed questions to well-formed question. | CS.cikm | 2019-11-03 |
| 348 | How Does BERT Answer Questions?: A Layer-Wise Analysis of Transformer Representations | BETTY VAN AKEN et. al. | In order to better understand BERT and other Transformer-based models, we present a layer-wise analysis of BERT’s hidden states. | CS.cikm | 2019-11-03 |
| 349 | Learning to Answer Complex Questions over Knowledge Bases with Query Composition | NIKITA BHUTANI et. al. | We propose a KB-QA system, TextRay, which answers complex questions using a novel decompose-execute-join approach. | CS.cikm | 2019-11-03 |
| 350 | MedTruth: A Semi-supervised Approach to Discovering Knowledge Condition Information from Multi-Source Medical Data | YANG DENG et. al. | In this paper, we aim to discovery medical knowledge conditions from texts to enrich KGs. | CS.cikm | 2019-11-03 |
| 351 | Message Passing for Complex Question Answering over Knowledge Graphs | SVITLANA VAKULENKO et. al. | We propose a novel approach for complex KGQA that uses unsupervised message passing, which propagates confidence scores obtained by parsing an input question and matching terms in the knowledge graph to a set of possible answers. | CS.cikm | 2019-11-03 |
| 352 | MRNN: A Multi-Resolution Neural Network with Duplex Attention for Document Retrieval in the Context of Question Answering | TOLGAHAN CAKALOGLU et. al. | In this paper, we devise a multi-resolution neural network(MRNN) to leverage the whole hierarchy of representations for document retrieval. | CS.arxiv | 2019-11-03 |
| 353 | Question Answering for Privacy Policies: Combining Computational and Legal Perspectives | ABHILASHA RAVICHANDER et. al. | We present PrivacyQA, a corpus consisting of 1750 questions about the privacy policies of mobile applications, and over 3500 expert annotations of relevant answers. | CS.arxiv | 2019-11-03 |
| 354 | Scene Graph based Image Retrieval — A case study on the CLEVR Dataset | SAHANA RAMNATH et. al. | Motivated by this, we propose a neural-symbolic approach for a one-shot retrieval of images from a large scale catalog, given the caption description. | CS.arxiv | 2019-11-03 |
| 355 | Semantically Driven Auto-completion | KONSTANTINE ARKOUDAS et. al. | We describe the auto-complete problem as it arises in this setting, the novel algorithms that we use to solve it, and report on the quality of the results and the efficiency of our approach. | CS.cikm | 2019-11-03 |
| 356 | A Discrete Hard EM Approach for Weakly Supervised Question Answering | SEWON MIN et. al. | In this paper, we show it is possible to convert such tasks into discrete latent variable learning problems with a precomputed, task-specific set of possible solutions (e.g. different mentions or equations) that contains one correct option. | CS.emnlp | 2019-11-02 |
| 357 | A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning | MINGHAO HU et. al. | In this paper, we introduce the Multi-Type Multi-Span Network (MTMSN), a neural reading comprehension model that combines a multi-type answer predictor designed to support various answer types (e.g., span, count, negation, and arithmetic expression) with a multi-span extraction method for dynamically producing one or multiple text spans. | CS.emnlp | 2019-11-02 |
| 358 | A Pilot Study for Chinese SQL Semantic Parsing | QINGKAI MIN et. al. | We compare character- and word-based encoders for a semantic parser, and different embedding schemes. | CS.emnlp | 2019-11-02 |
| 359 | Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations | XIN LV et. al. | In this paper, we propose a meta-based multi-hop reasoning method (Meta-KGR), which adopts meta-learning to learn effective meta parameters from high-frequency relations that could quickly adapt to few-shot relations. | CS.emnlp | 2019-11-02 |
| 360 | Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering | SHIYUE ZHANG et. al. | We propose two ways to generate synthetic QA pairs: generate new questions from existing articles or collect QA pairs from new articles. | CS.emnlp | 2019-11-02 |
| 361 | Answering Complex Open-domain Questions Through Iterative Query Generation | PENG QI et. al. | We present GoldEn (Gold Entity) Retriever, which iterates between reading context and retrieving more supporting documents to answer open-domain multi-hop questions. | CS.emnlp | 2019-11-02 |
| 362 | Answering Conversational Questions on Structured Data without Logical Forms | THOMAS MUELLER et. al. | We present a novel approach to answering sequential questions based on structured objects such as knowledge bases or tables without using a logical form as an intermediate representation. | CS.emnlp | 2019-11-02 |
| 363 | Answers Unite! Unsupervised Metrics for Reinforced Summarization Models | THOMAS SCIALOM et. al. | We thus explore and propose alternative evaluation measures: the reported human-evaluation analysis shows that the proposed metrics, based on Question Answering, favorably compare to ROUGE — with the additional property of not requiring reference summaries. | CS.emnlp | 2019-11-02 |
| 364 | Asking Clarification Questions in Knowledge-Based Question Answering | JINGJING XU et. al. | In this paper, we construct a new clarification dataset, CLAQUA, with nearly 40K open-domain examples. | CS.emnlp | 2019-11-02 |
| 365 | Bridging the Gap between Relevance Matching and Semantic Matching for Short Text Similarity Modeling | JINFENG RAO et. al. | To bridge this gap, we propose a novel model, HCAN{\textasciitilde}(Hybrid Co-Attention Network), that comprises (1) a hybrid encoder module that includes ConvNet-based and LSTM-based encoders, (2) a relevance matching module that measures soft term matches with importance weighting at multiple granularities, and (3) a semantic matching module with co-attention mechanisms that capture context-aware semantic relatedness. | CS.emnlp | 2019-11-02 |
| 366 | Can You Unpack That? Learning to Rewrite Questions-in-Context | AHMED ELGOHARY et. al. | We introduce the task of question-in-context rewriting: given the context of a conversation’s history, rewrite a context-dependent into a self-contained question with the same answer. | CS.emnlp | 2019-11-02 |
| 367 | Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning | LIFU HUANG et. al. | In this paper, we introduce Cosmos QA, a large-scale dataset of 35,600 problems that require commonsense-based reading comprehension, formulated as multiple-choice questions. | CS.emnlp | 2019-11-02 |
| 368 | Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering | SORAVIT CHANGPINYO et. al. | In this paper, we examine the effect of decoupling box proposal and featurization for down-stream tasks. | CS.emnlp | 2019-11-02 |
| 369 | Do NLP Models Know Numbers? Probing Numeracy in Embeddings | ERIC WALLACE et. al. | We begin by investigating the numerical reasoning capabilities of a state-of-the-art question answering model on the DROP dataset. We find this model excels on questions that require numerical reasoning, i.e., it already captures numeracy. | CS.emnlp | 2019-11-02 |
| 370 | Don’t Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases | CHRISTOPHER CLARK et. al. | In this paper, we show that if we have prior knowledge of such biases, we can train a model to be more robust to domain shift. | CS.emnlp | 2019-11-02 |
| 371 | Dual Attention Networks for Visual Reference Resolution in Visual Dialog | GI-CHEON KANG et. al. | In this paper, we propose Dual Attention Networks (DAN) for visual reference resolution in VisDial. | CS.emnlp | 2019-11-02 |
| 372 | Effective Use of Transformer Networks for Entity Tracking | ADITYA GUPTA et. al. | In this paper, we explore the use of pre-trained transformer networks for entity tracking tasks in procedural text. | CS.emnlp | 2019-11-02 |
| 373 | Exploring Diverse Expressions for Paraphrase Generation | LIHUA QIAN et. al. | In this paper, we propose a novel approach with two discriminators and multiple generators to generate a variety of different paraphrases. | CS.emnlp | 2019-11-02 |
| 374 | Finding Generalizable Evidence by Learning to Convince Qtextbackslash&A Models | ETHAN PEREZ et. al. | We propose a system that finds the strongest supporting evidence for a given answer to a question, using passage-based question-answering (QA) as a testbed. | CS.emnlp | 2019-11-02 |
| 375 | Fine-tune BERT with Sparse Self-Attention Mechanism | BAIYUN CUI et. al. | In this paper, we develop a novel Sparse Self-Attention Fine-tuning model (referred as SSAF) which integrates sparsity into self-attention mechanism to enhance the fine-tuning performance of BERT. | CS.emnlp | 2019-11-02 |
| 376 | Generating Highly Relevant Questions | JIAZUO QIU et. al. | The neural seq2seq based question generation (QG) is prone to generating generic and undiversified questions that are poorly relevant to the given passage and target answer. In this paper, we propose two methods to address the issue. | CS.emnlp | 2019-11-02 |
| 377 | GeoSQA: A Benchmark for Scenario-based Question Answering in the Geography Domain at High School Level | ZIXIAN HUANG et. al. | In this paper, we introduce the GeoSQA dataset. | CS.emnlp | 2019-11-02 |
| 378 | How to Pre-Train Your Model? Comparison of Different Pre-Training Models for Biomedical Question Answering | SANJAY KAMATH et. al. | We compare two pre-training models based on reading comprehension and open domain question answering models and determine the performance when fine-tuned and tested over BIOASQ question answering dataset. | CS.arxiv | 2019-11-02 |
| 379 | Improving Answer Selection and Answer Triggering using Hard Negatives | SAWAN KUMAR et. al. | In this paper, we establish the effectiveness of using hard negatives, coupled with a siamese network and a suitable loss function, for the tasks of answer selection and answer triggering. | CS.emnlp | 2019-11-02 |
| 380 | Incorporating Contextual and Syntactic Structures Improves Semantic Similarity Modeling | LINQING LIU et. al. | However, such structure priors have not been well exploited in previous work for semantic modeling. To examine their effectiveness, we start with the Pairwise Word Interaction Model, one of the best models according to a recent reproducibility study, then introduce components for modeling context and structure using multi-layer BiLSTMs and TreeLSTMs. | CS.emnlp | 2019-11-02 |
| 381 | Incorporating External Knowledge into Machine Reading for Generative Question Answering | BIN BI et. al. | In this paper, we propose a new neural model, Knowledge-Enriched Answer Generator (KEAG), which is able to compose a natural answer by exploiting and aggregating evidence from all four information sources available: question, passage, vocabulary and knowledge. | CS.emnlp | 2019-11-02 |
| 382 | Interactive Language Learning by Question Answering | XINGDI YUAN et. al. | We propose and evaluate a set of baseline models for the QAit task that includes deep reinforcement learning agents. | CS.emnlp | 2019-11-02 |
| 383 | Language Models as Knowledge Bases? | FABIO PETRONI et. al. | We present an in-depth analysis of the relational knowledge already present (without fine-tuning) in a wide range of state-of-the-art pretrained language models. | CS.emnlp | 2019-11-02 |
| 384 | Learning with Limited Data for Multilingual Reading Comprehension | KYUNGJAE LEE et. al. | To address this challenge, we propose a weakly-supervised framework that quantifies such noises from automatically generated labels, to deemphasize or fix noisy data in training. | CS.emnlp | 2019-11-02 |
| 385 | Let’s Ask Again: Refine Network for Automatic Question Generation | PREKSHA NEMA et. al. | In this work, we focus on the task of Automatic Question Generation (AQG) where given a passage and an answer the task is to generate the corresponding question. | CS.emnlp | 2019-11-02 |
| 386 | Leveraging Frequent Query Substructures to Generate Formal Queries for Complex Question Answering | JIWEI DING et. al. | In this paper, we propose SubQG, a new query generation approach based on frequent query substructures, which helps rank the existing (but nonsignificant) query structures or build new query structures. | CS.emnlp | 2019-11-02 |
| 387 | MICRON: Multigranular Interaction for Contextualizing RepresentatiON in Non-factoid Question Answering | HOJAE HAN et. al. | Specifically, we propose MICRON: Multigranular Interaction for Contextualizing RepresentatiON, a novel approach which derives contextualized uni-gram representation from n-grams. | CS.emnlp | 2019-11-02 |
| 388 | Movie Plot Analysis via Turning Point Identification | PINELOPI PAPALAMPIDI et. al. | We propose the task of turning point identification in movies as a means of analyzing their narrative structure. We introduce a dataset consisting of screenplays and plot synopses annotated with turning points and present an end-to-end neural network model that identifies turning points in plot synopses and projects them onto scenes in screenplays. | CS.emnlp | 2019-11-02 |
| 389 | Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering | ZHIGUO WANG et. al. | To tackle this issue, we propose a multi-passage BERT model to globally normalize answer scores across all passages of the same question, and this change enables our QA model find better answers by utilizing more passages. | CS.emnlp | 2019-11-02 |
| 390 | Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base | TAO SHEN et. al. | To tackle these issues, we propose an innovative multi-task learning framework where a pointer-equipped semantic parsing model is designed to resolve coreference in conversations, and naturally empower joint learning with a novel type-aware entity detection model. | CS.emnlp | 2019-11-02 |
| 391 | Multi-View Domain Adapted Sentence Embeddings for Low-Resource Unsupervised Duplicate Question Detection | NINA POERNER et. al. | We address the problem of Duplicate Question Detection (DQD) in low-resource domain-specific Community Question Answering forums. | CS.emnlp | 2019-11-02 |
| 392 | PubMedQA: A Dataset for Biomedical Research Question Answering | QIAO JIN et. al. | We introduce PubMedQA, a novel biomedical question answering (QA) dataset collected from PubMed abstracts. | CS.emnlp | 2019-11-02 |
| 393 | PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text | HAITIAN SUN et. al. | We describe PullNet, an integrated framework for (1) learning what to retrieve and (2) reasoning with this heterogeneous information to find the best answer. | CS.emnlp | 2019-11-02 |
| 394 | QAInfomax: Learning Robust Question Answering System by Mutual Information Maximization | YI-TING YEH et. al. | To address this problem, we propose QAInfomax as a regularizer in reading comprehension systems by maximizing mutual information among passages, a question, and its answer. | CS.emnlp | 2019-11-02 |
| 395 | Ranking and Sampling in Open-Domain Question Answering | YANFU XU et. al. | In this paper, we first introduce a ranking model leveraging the paragraph-question and the paragraph-paragraph relevance to compute a confidence score for each paragraph. Furthermore, based on the scores, we design a modified weighted sampling strategy for training to mitigate the influence of the noisy and distracting paragraphs. | CS.emnlp | 2019-11-02 |
| 396 | Revealing the Importance of Semantic Retrieval for Machine Reading at Scale | YIXIN NIE et. al. | In this work, we give general guidelines on system design for MRS by proposing a simple yet effective pipeline system with special consideration on hierarchical semantic retrieval at both paragraph and sentence level, and their potential effects on the downstream task. | CS.emnlp | 2019-11-02 |
| 397 | Revisiting the Evaluation of Theory of Mind through Question Answering | MATTHEW LE et. al. | In this work, we revisit the evaluation of theory of mind through question answering. | CS.emnlp | 2019-11-02 |
| 398 | Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning | YICHEN JIANG et. al. | In this work, we present an interpretable, controller-based Self-Assembling Neural Modular Network (Hu et al., 2017, 2018) for multi-hop reasoning, where we design four novel modules (Find, Relocate, Compare, NoOp) to perform unique types of language reasoning. | CS.emnlp | 2019-11-02 |
| 399 | Single Training Dimension Selection for Word Embedding with PCA | YU WANG | In this paper, we present a fast and reliable method based on PCA to select the number of dimensions for word embeddings. | CS.emnlp | 2019-11-02 |
| 400 | Social IQa: Commonsense Reasoning about Social Interactions | MAARTEN SAP et. al. | We introduce Social IQa, the first large-scale benchmark for commonsense reasoning about social situations. | CS.emnlp | 2019-11-02 |
| 401 | Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation | ARIJIT RAY et. al. | In this work, we introduce a dataset, ConVQA, and metrics that enable quantitative evaluation of consistency in VQA. Further, we propose a consistency-improving data augmentation module, a Consistency Teacher Module (CTM). | CS.emnlp | 2019-11-02 |
| 402 | Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks | HAOYANG HUANG et. al. | We present Unicoder, a universal language encoder that is insensitive to different languages. | CS.emnlp | 2019-11-02 |
| 403 | Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs | ANGELA FAN et. al. | We propose constructing a local graph structured knowledge base for each query, which compresses the web search information and reduces redundancy. | CS.emnlp | 2019-11-02 |
| 404 | Video Dialog via Progressive Inference and Cross-Transformer | WEIKE JIN et. al. | In this paper, we introduce a novel progressive inference mechanism for video dialog, which progressively updates query information based on dialog history and video content until the agent think the information is sufficient and unambiguous. | CS.emnlp | 2019-11-02 |
| 405 | What’s Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering | TUSHAR KHOT et. al. | We propose jointly training a model to simultaneously fill this knowledge gap and compose it with the provided partial knowledge. | CS.emnlp | 2019-11-02 |
| 406 | YouMakeup: A Large-Scale Domain-Specific Multimodal Dataset for Fine-Grained Semantic Comprehension | WEIYING WANG et. al. | In this work, we introduce YouMakeup, a large-scale multimodal instructional video dataset to support fine-grained semantic comprehension research in specific domain. | CS.emnlp | 2019-11-02 |
| 407 | A neural document language modeling framework for spoken document retrieval | LI-PHEN 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.arxiv | 2019-10-31 |
| 408 | Do Multi-hop Readers Dream of Reasoning Chains? | HAOYU WANG et. al. | In this paper we conduct a systematic analysis to assess such an ability of various existing models proposed for multi-hop QA tasks. | CS.arxiv | 2019-10-31 |
| 409 | TAB-VCR: Tags and Attributes based Visual Commonsense Reasoning Baselines | JINGXIANG LIN et. al. | Reasoning is an important ability that we learn from a very early age. | CS.arxiv | 2019-10-31 |
| 410 | What Question Answering can Learn from Trivia Nerds | JORDAN BOYD-GRABER | We argue that creating a question answering 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.arxiv | 2019-10-31 |
| 411 | Ensembling Strategies for Answering Natural Questions | ANTHONY FERRITTO et. al. | In this work, we investigate a number of ensembling techniques and demonstrate a strategy which improves our F1 score for short answers on the dev set for NQ by 2.3 F1 points over our single model (which outperforms the previous SOTA by 1.9 F1 points). | CS.arxiv | 2019-10-30 |
| 412 | Let Me Know What to Ask: Interrogative-Word-Aware Question Generation | JUNMO KANG et. al. | In this work, we propose Interrogative-Word-Aware Question Generation (IWAQG), a pipelined system composed of two modules: an interrogative word classifier and a QG model. | CS.arxiv | 2019-10-30 |
| 413 | Time to Take Emoji Seriously: They Vastly Improve Casual Conversational Models | PIETER DELOBELLE et. al. | With this in mind, we modify BERT to fully support emoji, both from the Unicode Standard and custom emoji. | CS.arxiv | 2019-10-30 |
| 414 | Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering | KAIXIN MA et. al. | In this paper, we perform a survey of recent commonsense QA methods and we provide a systematic analysis of popular knowledge resources and knowledge-integration methods, across benchmarks from multiple commonsense datasets. | CS.arxiv | 2019-10-30 |
| 415 | A Heuristically Modified FP-Tree for Ontology Learning with Applications in Education | SAFWAN SHATNAWI et. al. | We propose a heuristically modified FP-Tree for ontology learning from text. | CS.arxiv | 2019-10-29 |
| 416 | 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.arxiv | 2019-10-29 |
| 417 | Learning Rich Image Region Representation for Visual Question Answering | BEI LIU et. al. | We propose to boost VQA by leveraging more powerful feature extractors by improving the representation ability of both visual and text features and the ensemble of models. | CS.arxiv | 2019-10-29 |
| 418 | Sentence Embeddings for Russian NLU | DMITRY POPOV et. al. | We investigate the performance of sentence embeddings models on several tasks for the Russian language. Finally, we present datasets for multiple choice question answering and next sentence prediction in Russian. | CS.arxiv | 2019-10-29 |
| 419 | A Survey on Knowledge Graph Embeddings with Literals: Which model links better Literal-ly? | GENET ASEFA GESESE et. al. | This paper conducts a survey of KG embedding models which not only consider the structured information contained in the form of entities and relations in a KG but also the unstructured information represented as literals such as text, numerical values, images, etc. | CS.arxiv | 2019-10-28 |
| 420 | Multi-Module System for Open Domain Chinese Question Answering over Knowledge Base | YIYING YANG et. al. | For the task of open domain Knowledge Based Question Answering in CCKS2019, we propose a method combining information retrieval and semantic parsing. | CS.arxiv | 2019-10-28 |
| 421 | Thieves on Sesame Street! Model Extraction of BERT-based APIs | KALPESH KRISHNA et. al. | We study the problem of model extraction in natural language processing, in which an adversary with only query access to a victim model attempts to reconstruct a local copy of that model. | CS.arxiv | 2019-10-27 |
| 422 | On the Cross-lingual Transferability of Monolingual Representations | MIKEL ARTETXE et. al. | State-of-the-art unsupervised multilingual models (e.g., multilingual BERT) have been shown to generalize in a zero-shot cross-lingual setting. | CS.arxiv | 2019-10-25 |
| 423 | SpeechBERT: Cross-Modal Pre-trained Language Model for End-to-end Spoken Question Answering | YUNG-SUNG CHUANG et. al. | To bring this advantage of pre-trained language models into spoken question answering, we propose SpeechBERT, a cross-modal transformer-based pre-trained language model. | CS.arxiv | 2019-10-25 |
| 424 | A Survey on Recent Advances in Named Entity Recognition from Deep Learning models | VIKAS YADAV et. al. | We present a comprehensive survey of deep neural network architectures for NER, and contrast them with previous approaches to NER based on feature engineering and other supervised or semi-supervised learning algorithms. | CS.arxiv | 2019-10-24 |
| 425 | Adversarial Representation Learning for Text-to-Image Matching | NIKOLAOS SARAFIANOS et. al. | With that in mind, we introduce TIMAM: a Text-Image Modality Adversarial Matching approach that learns modality-invariant feature representations using adversarial and cross-modal matching objectives. | CS.iccv | 2019-10-24 |
| 426 | AttentionRNN: A Structured Spatial Attention Mechanism | SIDDHESH KHANDELWAL et. al. | In this paper we develop a novel structured spatial attention mechanism which is end-to-end trainable and can be integrated with any feed-forward convolutional neural network. | CS.iccv | 2019-10-24 |
| 427 | Compact Trilinear Interaction for Visual Question Answering | TUONG DO et. al. | Thus, to selectively utilize image, question and answer information, we propose a novel trilinear interaction model which simultaneously learns high level associations between these three inputs. | CS.iccv | 2019-10-24 |
| 428 | From Strings to Things: Knowledge-Enabled VQA Model That Can Read and Reason | AJEET KUMAR SINGH et. al. | In this work, we present a VQA model which can read scene texts and perform reasoning on a knowledge graph to arrive at an accurate answer. | CS.iccv | 2019-10-24 |
| 429 | Generating a Common Question from Multiple Documents using Multi-source Encoder-Decoder Models | WOON SANG CHO et. al. | We propose a new task of generating common question from multiple documents and present simple variant of an existing multi-source encoder-decoder framework, called the Multi-Source Question Generator (MSQG). | CS.arxiv | 2019-10-24 |
| 430 | Language Features Matter: Effective Language Representations for Vision-Language Tasks | ANDREA BURNS et. al. | We conclude that language features deserve more attention, which has been informed by experiments which compare different word embeddings, language models, and embedding augmentation steps on five common VL tasks: image-sentence retrieval, image captioning, visual question answering, phrase grounding, and text-to-clip retrieval. | CS.iccv | 2019-10-24 |
| 431 | Multi-Modality Latent Interaction Network for Visual Question Answering | PENG GAO et. al. | In this paper, we proposed the Multi-modality Latent Interaction module (MLI) to tackle this problem. | CS.iccv | 2019-10-24 |
| 432 | 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.arxiv | 2019-10-24 |
| 433 | Relation-Aware Graph Attention Network for Visual Question Answering | LINJIE LI et. al. | We propose a Relation-aware Graph Attention Network (ReGAT), which encodes each image into a graph and models multi-type inter-object relations via a graph attention mechanism, to learn question-adaptive relation representations. | CS.iccv | 2019-10-24 |
| 434 | Scene Text Visual Question Answering | ALI FURKAN BITEN et. al. | In this work, we present a new dataset, ST-VQA, that aims to highlight the importance of exploiting high-level semantic information present in images as textual cues in the Visual Question Answering process. | CS.iccv | 2019-10-24 |
| 435 | SegEQA: Video Segmentation Based Visual Attention for Embodied Question Answering | HAONAN LUO et. al. | To tackle these problems, we propose a segmentation based visual attention mechanism for Embodied Question Answering. | CS.iccv | 2019-10-24 |
| 436 | U-CAM: Visual Explanation Using Uncertainty Based Class Activation Maps | BADRI N. PATRO et. al. | Towards this, we propose a method that obtains gradient-based certainty estimates that also provide visual attention maps. | CS.iccv | 2019-10-24 |
| 437 | VrR-VG: Refocusing Visually-Relevant Relationships | YUANZHI LIANG et. al. | To encourage further development in visual relationships, we propose a novel method to mine more valuable relationships by automatically pruning visually-irrelevant relationships. We construct a new scene graph dataset named Visually-Relevant Relationships Dataset (VrR-VG) based on Visual Genome. | CS.iccv | 2019-10-24 |
| 438 | Why Does a Visual Question Have Different Answers? | NILAVRA BHATTACHARYA et. al. | We propose a taxonomy of nine plausible reasons, and create two labelled datasets consisting of 45,000 visual questions indicating which reasons led to answer differences. We then propose a novel problem of predicting directly from a visual question which reasons will cause answer differences as well as a novel algorithm for this purpose. | CS.iccv | 2019-10-24 |
| 439 | A Novel Approach for Automatic Bengali Question Answering System using Semantic Similarity Analysis | ARIJIT DAS et. al. | In this paper, an approach is described to find out the semantically relevant answers in the Bengali dataset. | CS.arxiv | 2019-10-23 |
| 440 | BanditRank: Learning to Rank Using Contextual Bandits | PHANIDEEP GAMPA et. al. | We propose an extensible deep learning method that uses reinforcement learning to train neural networks for offline ranking in information retrieval (IR). | CS.arxiv | 2019-10-23 |
| 441 | Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer | COLIN RAFFEL et. al. | In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts every language problem into a text-to-text format. To facilitate future work on transfer learning for NLP, we release our dataset, pre-trained models, and code. | CS.arxiv | 2019-10-23 |
| 442 | Relation Module for Non-answerable Prediction on Question Answering | KEVIN HUANG et. al. | In this paper, we aim to improve a MRC model’s ability to determine whether a question has an answer in a given context (e.g. the recently proposed SQuAD 2.0 task). | CS.arxiv | 2019-10-23 |
| 443 | Capturing Greater Context for Question Generation | LUU ANH TUAN et. al. | Our goal is to incorporate interactions across multiple sentences to generate realistic questions for long documents. | CS.arxiv | 2019-10-22 |
| 444 | 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.arxiv | 2019-10-22 |
| 445 | Question Answering over Knowledge Graphs via Structural Query Patterns | WEIGUO ZHENG et. al. | Distinct from the existing methods that are based on semantic parsing or templates, we propose an effective approach powered by a novel notion, structural query pattern, in this paper. | CS.arxiv | 2019-10-22 |
| 446 | Towards Combinational Relation Linking over Knowledge Graphs | WEIGUO ZHENG et. al. | In this paper, we focus on the task of combinational relation linking over knowledge graphs. | CS.arxiv | 2019-10-22 |
| 447 | Domain-agnostic Question-Answering with Adversarial Training | SEANIE LEE et. al. | In this paper, we utilize an adversarial training framework for domain generalization in Question Answering (QA) task. | CS.arxiv | 2019-10-21 |
| 448 | MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension | ADAM FISCH et. al. | We present the results of the Machine Reading for Question Answering (MRQA) 2019 shared task on evaluating the generalization capabilities of reading comprehension systems. | CS.arxiv | 2019-10-21 |
| 449 | Enforcing Reasoning in Visual Commonsense Reasoning | HAMMAD A. AYYUBI et. al. | In this paper, we seek to address these issues by proposing an end-to-end trainable model which considers both answers and their reasons jointly. | CS.arxiv | 2019-10-20 |
| 450 | Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System | ZE YANG et. al. | To tackle this challenge, we propose a Two-stage Multi-teacher Knowledge Distillation (TMKD for short) method for web Question Answering system. | CS.arxiv | 2019-10-18 |
| 451 | Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs | ANGELA FAN et. al. | We propose constructing a local graph structured knowledge base for each query, which compresses the web search information and reduces redundancy. | CS.arxiv | 2019-10-18 |
| 452 | 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.arxiv | 2019-10-17 |
| 453 | Question Classification with Deep Contextualized Transformer | HAOZHENG LUO et. al. | We build on prior work and develop a new method to handle the Question and Answer problem with the Deep Contextualized Transformer to manage some aberrant expressions. | CS.arxiv | 2019-10-17 |
| 454 | Relational Graph Representation Learning for Open-Domain Question Answering | SALVATORE VIVONA et. al. | We introduce a relational graph neural network with bi-directional attention mechanism and hierarchical representation learning for open-domain question answering task. | CS.arxiv | 2019-10-17 |
| 455 | SetExpan: Corpus-Based Set Expansion via Context Feature Selection and Rank Ensemble | JIAMING SHEN et. al. | In this study, we propose a novel framework, SetExpan, which tackles this problem, with two techniques: (1) a context feature selection method that selects clean context features for calculating entity-entity distributional similarity, and (2) a ranking-based unsupervised ensemble method for expanding entity set based on denoised context features. | CS.arxiv | 2019-10-17 |
| 456 | Universal Text Representation from BERT: An Empirical Study | XIAOFEI MA et. al. | We present a systematic investigation of layer-wise BERT activations for general-purpose text representations to understand what linguistic information they capture and how transferable they are across different tasks. | CS.arxiv | 2019-10-17 |
| 457 | Bridging the Knowledge Gap: Enhancing Question Answering with World and Domain Knowledge | TRAVIS R. GOODWIN et. al. | In this paper we present OSCAR (Ontology-based Semantic Composition Augmented Regularization), a method for injecting task-agnostic knowledge from an Ontology or knowledge graph into a neural network during pretraining. | CS.arxiv | 2019-10-16 |
| 458 | 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.arxiv | 2019-10-16 |
| 459 | Why can’t memory networks read effectively? | SIMON �USTER et. al. | We propose network adaptations that can serve as simple remedies. | CS.arxiv | 2019-10-16 |
| 460 | Efficiently Embedding Dynamic Knowledge Graphs | TIANXING WU et. al. | In this paper, to tackle the aforementioned problem, we propose a new context-aware Dynamic Knowledge Graph Embedding (DKGE) method which supports the embedding learning in an online fashion. | CS.arxiv | 2019-10-15 |
| 461 | Unsupervised Question Answering for Fact-Checking | MAYANK JOBANPUTRA | In this paper, we propose an unsupervised question-answering based approach for a similar task, fact-checking. | CS.arxiv | 2019-10-15 |
| 462 | Structured Pruning of a BERT-based Question Answering Model | J. S. MCCARLEY et. al. | In this paper, we investigate compressing BERT- and RoBERTa-based question answering systems by structured pruning of parameters from the underlying trained transformer model. | CS.arxiv | 2019-10-14 |
| 463 | Whatcha lookin’ at? DeepLIFTing BERT’s Attention in Question Answering | EKATERINA ARKHANGELSKAIA et. al. | In this paper, we investigate one such model, BERT for question-answering, with the aim to analyze why it is able to achieve significantly better results than other models. | CS.arxiv | 2019-10-14 |
| 464 | Learning Analogy-Preserving Sentence Embeddings for Answer Selection | AISSATOU DIALLO et. al. | Using analogical inference as our use case, we propose a framework and a neural network architecture for learning dedicated sentence embeddings that preserve analogical properties in the semantic space. | CS.arxiv | 2019-10-11 |
| 465 | Multi-modal Deep Analysis for Multimedia | WENWU ZHU et. al. | In this article, we present a deep and comprehensive overview for multi-modal analysis in multimedia. We introduce two scientific research problems, data-driven correlational representation and knowledge-guided fusion for multimedia analysis. | CS.arxiv | 2019-10-11 |
| 466 | Multilingual Question Answering from Formatted Text applied to Conversational Agents | WISSAM SIBLINI et. al. | In this paper, we run experiments that show that multilingual BERT, trained to solve the complex Question Answering task defined in the English SQuAD dataset, is able to achieve the same task in Japanese and French. | CS.arxiv | 2019-10-10 |
| 467 | Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion | PHILIPP CHRISTMANN et. al. | As a solution, we develop CONVEX: an unsupervised method that can answer incomplete questions over a knowledge graph (KG) by maintaining conversation context using entities and predicates seen so far and automatically inferring missing or ambiguous pieces for follow-up questions. | CS.arxiv | 2019-10-08 |
| 468 | Modulated Self-attention Convolutional Network for VQA | JEAN-BENOIT DELBROUCK et. al. | In this paper, we propose to modulate by a linguistic input a CNN augmented with self-attention. | CS.arxiv | 2019-10-08 |
| 469 | Multi-hop Question Answering via Reasoning Chains | JIFAN CHEN et. al. | We propose a method to extract a discrete reasoning chain over the text, which consists of a series of sentences leading to the answer. | CS.arxiv | 2019-10-07 |
| 470 | 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 hidden representations. | CS.arxiv | 2019-10-06 |
| 471 | On the Limits of Learning to Actively Learn Semantic Representations | OMRI KOSHOREK et. al. | In this work, we examine LTAL for learning semantic representations, such as QA-SRL. | CS.arxiv | 2019-10-05 |
| 472 | Multi-level Gated Recurrent Neural Network for Dialog Act Classification | WEI LI et. al. | In this paper we focus on the problem of dialog act (DA) labelling. | CS.arxiv | 2019-10-04 |
| 473 | Template-based Minor Embedding for Adiabatic Quantum Optimization | THIAGO SERRA et. al. | This has spurred work on preprocessing algorithms for embedding the graph representing problem variables with quadratic terms in the hardware graph representing qubits adjacencies, such as the Chimera graph in hardware produced by D-Wave Systems.In this paper, we use integer linear programming to search for an embedding of the problem graph into certain classes of minors of the Chimera graph, which we call template embeddings. | CS.arxiv | 2019-10-04 |
| 474 | Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks | MOKANARANGAN THAYAPARAN et. al. | This paper proposes Document Graph Network (DGN), a message passing architecture for the identification of supporting facts over a graph-structured representation of text. | CS.arxiv | 2019-10-01 |
| 475 | Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations | CHRISTIAN HADIWINOTO et. al. | In this paper, we explore different strategies of integrating pre-trained contextualized word representations and our best strategy achieves accuracies exceeding the best prior published accuracies by significant margins on multiple benchmark WSD datasets. | CS.arxiv | 2019-10-01 |
| 476 | 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.arxiv | 2019-10-01 |
| 477 | On Incorporating Semantic Prior Knowledge in Deep Learning Through Embedding-Space Constraints | DAMIEN TENEY et. al. | We present a general technique to supplement supervised training with prior knowledge expressed as relations between training instances. | CS.arxiv | 2019-09-30 |
| 478 | OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction | XU HAN et. al. | OpenNRE is an open-source and extensible toolkit that provides a unified framework to implement neural models for relation extraction (RE). | CS.arxiv | 2019-09-28 |
| 479 | Distantly Supervised Question Parsing | HAMID ZAFAR et. al. | In this paper, we propose a distantly supervised learning framework based on reinforcement learning to learn the mentions of entities and relations in questions. | CS.arxiv | 2019-09-27 |
| 480 | Spoken Conversational Search for General Knowledge | LINA M. ROJAS-BARAHONA et. al. | We present a spoken conversational question answering proof of concept that is able to answer questions about general knowledge from Wikidata. | CS.arxiv | 2019-09-26 |
| 481 | Overcoming Data Limitation in Medical Visual Question Answering | BINH D. NGUYEN et. al. | In this paper, we propose a novel medical VQA framework that overcomes the labeled data limitation. | CS.arxiv | 2019-09-25 |
| 482 | Question Answering is a Format; When is it Useful? | MATT GARDNER et. al. | We discuss when a task is correctly described as question answering, and when a task is usefully posed as question answering, instead of using some other format. | CS.arxiv | 2019-09-25 |
| 483 | 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.arxiv | 2019-09-25 |
| 484 | An Empirical Study of Content Understanding in Conversational Question Answering | TING-RUI CHIANG et. al. | 2) Do the models well utilize the conversation content when answering questions? | CS.arxiv | 2019-09-24 |
| 485 | Technical report on Conversational Question Answering | YING JU et. al. | In this project, we propose a new system RoBERTa + AT +KD, which involves rationale tagging multi-task, adversarial training, knowledge distillation and a linguistic post-process strategy. | CS.arxiv | 2019-09-24 |
| 486 | Unified Vision-Language Pre-Training for Image Captioning and VQA | LUOWEI ZHOU et. al. | This paper presents a unified Vision-Language Pre-training (VLP) model. | CS.arxiv | 2019-09-24 |
| 487 | Non-monotonic Logical Reasoning Guiding Deep Learning for Explainable Visual Question Answering | HEATHER RILEY et. al. | Training these models requires a large labeled dataset and considerable computational resources. | CS.arxiv | 2019-09-23 |
| 488 | Portuguese Named Entity Recognition using BERT-CRF | F�BIO SOUZA et. al. | In this work, we train Portuguese BERT models and employ a BERT-CRF architecture to the NER task on the Portuguese language, combining the transfer capabilities of BERT with the structured predictions of CRF. | CS.arxiv | 2019-09-23 |
| 489 | Explainable High-order Visual Question Reasoning: A New Benchmark and Knowledge-routed Network | QINGXING CAO et. al. | In this work, we propose a new HVQR benchmark for evaluating explainable and high-order visual question reasoning ability with three distinguishable merits: 1) the questions often contain one or two relationship triplets, which requires the model to have the ability of multistep reasoning to predict plausible answers; 2) we provide an explicit evaluation on a multistep reasoning process that is constructed with image scene graphs and commonsense knowledge bases; and 3) each relationship triplet in a large-scale knowledge base only appears once among all questions, which poses challenges for existing networks that often attempt to overfit the knowledge base that already appears in the training set and enforces the models to handle unseen questions and knowledge fact usage. | CS.arxiv | 2019-09-22 |
| 490 | Designing dialogue systems: A mean, grumpy, sarcastic chatbot in the browser | SUZANA ILI? et. al. | In this work we explore a deep learning-based dialogue system that generates sarcastic and humorous responses from a conversation design perspective. | CS.arxiv | 2019-09-20 |
| 491 | Quantifying the Impact of Cognitive Biases in Question-Answering Systems | KEITH BURGHARDT et. al. | We end our paper by discussing the novel ways we can apply these findings to substantially improve how high-quality answers are found in question-answering systems. | CS.arxiv | 2019-09-20 |
| 492 | How Additional Knowledge can Improve Natural Language Commonsense Question Answering? | ARINDAM MITRA et. al. | Our goal in this work is to develop methods to incorporate additional (commonsense) knowledge into language model-based approaches for better question-answering in such domains. | CS.arxiv | 2019-09-19 |
| 493 | Learning Sparse Mixture of Experts for Visual Question Answering | VARDAAN PAHUJA et. al. | In this project, we propose an efficient and modular neural architecture for the VQA task with focus on the CNN module. | CS.arxiv | 2019-09-19 |
| 494 | Look, Read and Enrich. Learning from Scientific Figures and their Captions | JOSE MANUEL GOMEZ-PEREZ et. al. | In this paper we investigate what can be learnt by looking at a large number of figures and reading their captions, and introduce a figure-caption correspondence learning task that makes use of our observations. | CS.arxiv | 2019-09-19 |
| 495 | Triplet-Aware Scene Graph Embeddings | BRIGIT SCHROEDER et. al. | In this work, we train scene graph embeddings in a layout generation task with different forms of supervision, specifically introducing triplet super-vision and data augmentation. | CS.arxiv | 2019-09-19 |
| 496 | Conversational AI : Open Domain Question Answering and Commonsense Reasoning | KINJAL BASU | Our research is focused on making a human-like question answering system which can answer rationally. | CS.arxiv | 2019-09-18 |
| 497 | Pre-trained Language Model for Biomedical Question Answering | WONJIN YOON et. al. | In this paper, we investigate the performance of BioBERT, a pre-trained biomedical language model, in answering biomedical questions including factoid, list, and yes/no type questions. | CS.arxiv | 2019-09-18 |
| 498 | Inverse Visual Question Answering with Multi-Level Attentions | YASER ALWATTER et. al. | In this paper, we propose a novel deep multi-level attention model to address inverse visual question answering. | CS.arxiv | 2019-09-17 |
| 499 | Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering | AMEYA GODBOLE et. al. | This paper introduces an IR technique that uses information of entities present in the initially retrieved evidence to learn to `\emph{hop}’ to other relevant evidence. | CS.arxiv | 2019-09-17 |
| 500 | Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering | WENHAN XIONG et. al. | To resolve this issue, we introduce a new sub-problem of open-domain multi-hop QA, which aims to recognize the bridge (\emph{i.e.}, the anchor that links to the answer passage) from the context of a set of start passages with a reading comprehension model. | CS.arxiv | 2019-09-17 |
| 501 | KorQuAD1.0: Korean QA Dataset for Machine Reading Comprehension | SEUNGYOUNG LIM et. al. | We present Korean Question Answering Dataset(KorQuAD), a large-scale Korean dataset for extractive machine reading comprehension task. | CS.arxiv | 2019-09-16 |
| 502 | PubMedQA: A Dataset for Biomedical Research Question Answering | QIAO JIN et. al. | We introduce PubMedQA, a novel biomedical question answering (QA) dataset collected from PubMed abstracts. | CS.arxiv | 2019-09-13 |
| 503 | Towards Open-Domain Named Entity Recognition via Neural Correction Models | MENGDI ZHU et. al. | In this work, we propose a semi-supervised annotation framework to make full use of abstracts from Wikipedia and obtain a large and high-quality dataset called AnchorNER. | CS.arxiv | 2019-09-13 |
| 504 | Finding Generalizable Evidence by Learning to Convince Q&A Models | ETHAN PEREZ et. al. | We propose a system that finds the strongest supporting evidence for a given answer to a question, using passage-based question-answering (QA) as a testbed. | CS.arxiv | 2019-09-12 |
| 505 | Measuring Domain Portability and ErrorPropagation in Biomedical QA | STEFAN HOSEIN et. al. | In this work we present Google’s submission to the BioASQ 7 biomedical question answering (QA) task (specifically Task 7b, Phase B). | CS.arxiv | 2019-09-12 |
| 506 | Frustratingly Easy Natural Question Answering | LIN PAN et. al. | In this paper, we outline these algorithmic components such as Attention-over-Attention, coupled with data augmentation and ensembling strategies that have shown to yield state-of-the-art results on benchmark datasets like SQuAD, even achieving super-human performance. | CS.arxiv | 2019-09-11 |
| 507 | How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations | BETTY VAN AKEN et. al. | In order to better understand BERT and other Transformer-based models, we present a layer-wise analysis of BERT’s hidden states. | CS.arxiv | 2019-09-11 |
| 508 | Question Generation by Transformers | KETTIP KRIANGCHAIVECH et. al. | A machine learning model was developed to automatically generate questions from Wikipedia passages using transformers, an attention-based model eschewing the paradigm of existing recurrent neural networks (RNNs). | CS.arxiv | 2019-09-09 |
| 509 | Large Scale Question Answering using Tourism Data | DANISH CONTRACTOR et. al. | We introduce the novel task of answering entity-seeking recommendation questions using a collection of reviews that describe candidate answer entities. | CS.arxiv | 2019-09-08 |
| 510 | Abductive Reasoning as Self-Supervision for Common Sense Question Answering | SATHYANARAYANAN N. AAKUR et. al. | In this work, we explore the ability of current question-answering models to generalize – to both other domains as well as with restricted training data. | CS.arxiv | 2019-09-06 |
| 511 | 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.arxiv | 2019-09-06 |
| 512 | A Better Way to Attend: Attention with Trees for Video Question Answering | HONGYANG XUE et. al. | We propose a new attention model for video question answering. | CS.arxiv | 2019-09-05 |
| 513 | A Generalized Web Component for Domain-Independent Smart Assistants | YUSUF SERMET et. al. | The goal of this project is to pave the way for next-generation information systems by mitigating the challenges of developing voice-enabled and domain-informed smart assistants for communicating knowledge in any domain. | CS.arxiv | 2019-09-05 |
| 514 | An Empirical Study on the Characteristics of Question-Answering Process on Developer Forums | YI LI et. al. | In this paper, we empirically study three API forums including Twitter, eBay, and AdWords, to investigate the characteristics of question-answering process. | CS.arxiv | 2019-09-05 |
| 515 | From ‘F’ to ‘A’ on the N.Y. Regents Science Exams: An Overview of the Aristo Project | PETER CLARK et. al. | This paper reports unprecedented success on the Grade 8 New York Regents Science Exam, where for the first time a system scores more than 90% on the exam’s non-diagram, multiple choice (NDMC) questions. | CS.arxiv | 2019-09-04 |
| 516 | Attention-based Pairwise Multi-Perspective Convolutional Neural Network for Answer Selection in Question Answering | JAMSHID MOZAFARI et. al. | In this research, a model is proposed to select the most relevant answers to the factoid question from the candidate answers. | CS.arxiv | 2019-09-03 |
| 517 | Language Models as Knowledge Bases? | FABIO PETRONI et. al. | We present an in-depth analysis of the relational knowledge already present (without fine-tuning) in a wide range of state-of-the-art pretrained language models. | CS.arxiv | 2019-09-03 |
| 518 | Neural Attentive Bag-of-Entities Model for Text Classification | IKUYA YAMADA et. al. | This study proposes a Neural Attentive Bag-of-Entities model, which is a neural network model that performs text classification using entities in a knowledge base. | CS.arxiv | 2019-09-03 |
| 519 | PlotQA: Reasoning over Scientific Plots | NITESH METHANI et. al. | In this work, we aim to bridge this gap between existing datasets and real-world plots. | CS.arxiv | 2019-09-03 |
| 520 | 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.arxiv | 2019-09-01 |
| 521 | Answering Conversational Questions on Structured Data without Logical Forms | THOMAS M�LLER et. al. | We present a novel approach to answering sequential questions based on structured objects such as knowledge bases or tables without using a logical form as an intermediate representation. | CS.arxiv | 2019-08-30 |
| 522 | Interactive Language Learning by Question Answering | XINGDI YUAN et. al. | We propose and evaluate a set of baseline models for the QAit task that includes deep reinforcement learning agents. | CS.arxiv | 2019-08-28 |
| 523 | A Comparative Study of Younger and Older Adults’ Interaction with a Crowdsourcing Android TV App for Detecting Errors in TEDx Video Subtitles | KINGA SKORUPSKA et. al. | In this paper we report the results of a pilot study comparing the older and younger adults’ interaction with an Android TV application which enables users to detect errors in video subtitles. | CS.arxiv | 2019-08-27 |
| 524 | Incremental Improvement of a Question Answering System by Re-ranking Answer Candidates using Machine Learning | MICHAEL BARZ et. al. | Our contributions are: (1) we generate a QA training corpus starting from 877 answers from the customer care domain of T-Mobile Austria, (2) we implement a state-of-the-art QA pipeline using neural sentence embeddings that encode queries in the same space than the answer index, and (3) we evaluate the QA pipeline and our re-ranking approach using a separately provided test set. | CS.arxiv | 2019-08-27 |
| 525 | 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.arxiv | 2019-08-27 |
| 526 | Ensemble approach for natural language question answering problem | ANNA ANIOL et. al. | The best models have been selected, studied and compared with each other. | CS.arxiv | 2019-08-26 |
| 527 | Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks | SEUNGHYUN YOON et. al. | In this study, we propose a novel graph neural network called propagate-selector (PS), which propagates information over sentences to understand information that cannot be inferred when considering sentences in isolation. | CS.arxiv | 2019-08-24 |
| 528 | Revisiting Semantic Representation and Tree Search for Similar Question Retrieval | TONG GUO et. al. | This paper studies the performances of BERT combined with tree structure in short sentence ranking task. | CS.arxiv | 2019-08-22 |
| 529 | VL-BERT: Pre-training of Generic Visual-Linguistic Representations | WEIJIE SU et. al. | We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short). | CS.arxiv | 2019-08-22 |
| 530 | LXMERT: Learning Cross-Modality Encoder Representations from Transformers | HAO TAN et. al. | We thus propose the LXMERT (Learning Cross-Modality Encoder Representations from Transformers) framework to learn these vision-and-language connections. | CS.arxiv | 2019-08-20 |
| 531 | A Study of BERT for Non-Factoid Question-Answering under Passage Length Constraints | YOSI MASS et. al. | We study the use of BERT for non-factoid question-answering, focusing on the passage re-ranking task under varying passage lengths. | CS.arxiv | 2019-08-19 |
| 532 | Align, Mask and Select: A Simple Method for Incorporating Commonsense Knowledge into Language Representation Models | ZHI-XIU YE et. al. | We propose a pre-training approach for incorporating commonsense knowledge into language representation models. | CS.arxiv | 2019-08-19 |
| 533 | Question Answering based Clinical Text Structuring Using Pre-trained Language Model | JIAHUI QIU et. al. | In this paper, we present a question answering based clinical text structuring (QA-CTS) task to unify different specific tasks and make dataset shareable. | CS.arxiv | 2019-08-19 |
| 534 | Transfer in Deep Reinforcement Learning using Knowledge Graphs | PRITHVIRAJ AMMANABROLU et. al. | In this paper, we explore the use of knowledge graphs as a representation for domain knowledge transfer for training text-adventure playing reinforcement learning agents. | CS.arxiv | 2019-08-18 |
| 535 | What is needed for simple spatial language capabilities in VQA? | ALEXANDER KUHNLE et. al. | Following this approach, we focus on spatial language capabilities and investigate the question: what are the key ingredients to handle simple visual-spatial relations? | CS.arxiv | 2019-08-17 |
| 536 | CFO: A Framework for Building Production NLP Systems | RISHAV CHAKRAVARTI et. al. | This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production environments. | CS.arxiv | 2019-08-16 |
| 537 | Learning Representations and Agents for Information Retrieval | RODRIGO NOGUEIRA | This agent can leverage the effort that has been put into designing and running efficient storage and retrieval systems by learning how to best utilize them to accomplish a task. | CS.arxiv | 2019-08-16 |
| 538 | Abductive Commonsense Reasoning | CHANDRA BHAGAVATULA et. al. | We introduce a challenge dataset, ART, that consists of over 20k commonsense narrative contexts and 200k explanations. | CS.arxiv | 2019-08-15 |
| 539 | M-BERT: Injecting Multimodal Information in the BERT Structure | WASIFUR RAHMAN et. al. | In this paper, we inject multimodal information within the input space of BERT network for modeling multimodal language. | CS.arxiv | 2019-08-15 |
| 540 | Multi-class Hierarchical Question Classification for Multiple Choice Science Exams | DONGFANG XU et. al. | To address this, we present the largest challenge dataset for QC, containing 7,787 science exam questions paired with detailed classification labels from a fine-grained hierarchical taxonomy of 406 problem domains. | CS.arxiv | 2019-08-15 |
| 541 | FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension | YI-TING YEH et. al. | This paper proposes to explicitly model the information gain through dialogue reasoning in order to allow the model to focus on more informative cues. | CS.arxiv | 2019-08-14 |
| 542 | Fusion of Detected Objects in Text for Visual Question Answering | CHRIS ALBERTI et. al. | To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language. | CS.arxiv | 2019-08-14 |
| 543 | Reactive Multi-Stage Feature Fusion for Multimodal Dialogue Modeling | YI-TING YEH et. al. | This paper proposes an intuitive mechanism that fuses features and attention in multiple stages in order to well integrate multimodal features, and the results demonstrate its capability in the experiments. | CS.arxiv | 2019-08-14 |
| 544 | Towards Optimisation of Collaborative Question Answering over Knowledge Graphs | KULDEEP SINGH et. al. | In this paper, we tackle the problem of local optimisation of CQA frameworks and propose a three fold approach, which applies feature selection techniques with supervised machine learning approaches in order to identify the best performing components efficiently. | CS.arxiv | 2019-08-14 |
| 545 | VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering | C?T?LINA CANGEA et. al. | We investigate several models, adapted from popular VQA methods, on this new benchmark. In order to investigate the feasibility of EQA-type tasks, we build the VideoNavQA dataset that contains pairs of questions and videos generated in the House3D environment. | CS.arxiv | 2019-08-14 |
| 546 | Reasoning-Driven Question-Answering for Natural Language Understanding | DANIEL KHASHABI | In this thesis, we investigate the NLU problem through the QA task and focus on the aspects that make it a challenge for the current state-of-the-art technology. In the second part, we propose two new challenge datasets. In particular, we create two datasets of natural language questions where (i) the first one requires reasoning over multiple sentences; (ii) the second one requires temporal common sense reasoning. | CS.arxiv | 2019-08-13 |
| 547 | StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding | WEI WANG et. al. | Inspired by the linearization exploration work of Elman [8], we extend BERT to a new model, StructBERT, by incorporating language structures into pre-training. | CS.arxiv | 2019-08-13 |
| 548 | AmazonQA: A Review-Based Question Answering Task | MANSI GUPTA et. al. | To this end, we introduce a new dataset and propose a method that combines information retrieval techniques for selecting relevant reviews (given a question) and reading comprehension models for synthesizing an answer (given a question and review). | CS.arxiv | 2019-08-12 |
| 549 | Multimodal Unified Attention Networks for Vision-and-Language Interactions | ZHOU YU et. al. | Here we propose a general `unified attention’ model that simultaneously captures the intra- and inter-modal interactions of multimodal features and outputs their corresponding attended representations. | CS.arxiv | 2019-08-12 |
| 550 | A Generate-Validate Approach to Answering Questions about Qualitative Relationships | ARINDAM MITRA et. al. | In this paper, we show that instead of using a semantic parser to produce the logical form, if we apply the generate-validate framework i.e. generate a natural language description of the logical form and validate if the natural language description is followed from the input text, we get a better scope for transfer learning and our method outperforms the state-of-the-art by a large margin of 7.93%. | CS.arxiv | 2019-08-09 |
| 551 | AmazonQA: A Review-Based Question Answering Task | MANSI GUPTA et. al. | To this end, we introduce a new dataset and propose a method that combines informational retrieval techniques for selecting relevant reviews (given a question) and reading comprehension models�for synthesizing an answer (given a question and review). | CS.ijcai | 2019-08-09 |
| 552 | Data Poisoning Attack against Knowledge Graph Embedding | HENGTONG ZHANG et. al. | To fill this gap, we propose a collection of data poisoning attack strategies, which can effectively manipulate the plausibility of arbitrary targeted facts in a knowledge graph by adding or deleting facts on the graph. | CS.ijcai | 2019-08-09 |
| 553 | Densely Connected Attention Flow for Visual Question Answering | FEI LIU et. al. | Therefore, in this paper, we propose a novel DCAF (Densely Connected Attention Flow) framework for modeling dense interactions. | CS.ijcai | 2019-08-09 |
| 554 | Dual-View Variational Autoencoders for Semi-Supervised Text Matching | ZHONGBIN XIE et. al. | In this study, we propose to take the sentence-level embedding features and the word-level interaction features as two distinct views of a sentence pair, and unify them with a framework of Variational Autoencoders such that the sentence pair is matched in a semi-supervised manner. | CS.ijcai | 2019-08-09 |
| 555 | 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.ijcai | 2019-08-09 |
| 556 | Knowledge Base Question Answering with Topic Units | YUNSHI LAN et. al. | In this paper, we propose to perform topic unit linking where topic units cover a wider range of units of a KB. | CS.ijcai | 2019-08-09 |
| 557 | Knowledge-enhanced Hierarchical Attention for Community Question Answering with Multi-task and Adaptive Learning | MIN YANG et. al. | In this paper, we propose a Knowledge-enhanced Hierarchical Attention for community question answering with Multi-task learning and Adaptive learning (KHAMA). | CS.ijcai | 2019-08-09 |
| 558 | Leap-LSTM: Enhancing Long Short-Term Memory for Text Categorization | TING HUANG et. al. | To this end, we propose Leap-LSTM, an LSTM-enhanced model which dynamically leaps between words while reading texts. | CS.ijcai | 2019-08-09 |
| 559 | Neural Program Induction for KBQA Without Gold Programs or Query Annotations | GHULAM AHMED ANSARI et. al. | To deal with these, we propose a noise-resilient NPI model, Stable Sparse Reward based Programmer (SSRP) that evades noise-induced instability through continual retrospection and its comparison with current learning behavior. | CS.ijcai | 2019-08-09 |
| 560 | Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks | ZHU ZHANG et. al. | To tackle these problems, we propose a fast hierarchical convolutional self-attention encoder-decoder network. | CS.ijcai | 2019-08-09 |
| 561 | Out of Sight But Not Out of Mind: An Answer Set Programming Based Online Abduction Framework for Visual Sensemaking in Autonomous Driving | JAKOB SUCHAN et. al. | We demonstrate the need and potential of systematically integrated vision and semantics solutions for visual sensemaking (in the backdrop of autonomous driving). | CS.ijcai | 2019-08-09 |
| 562 | TEQUILA: Temporal Question Answering over Knowledge Bases | ZHEN JIA et. al. | We present TEQUILA, an enabler method for temporal QA that can run on top of any KB-QA engine. | CS.arxiv | 2019-08-09 |
| 563 | Weak Supervision Enhanced Generative Network for Question Generation | YUTONG WANG et. al. | To address this problem, we propose the Weakly Supervision Enhanced Generative Network (WeGen) which automatically discovers relevant features of the passage given the answer span in a weakly supervised manner to improve the quality of generated questions. | CS.ijcai | 2019-08-09 |
| 564 | From Two Graphs to N Questions: A VQA Dataset for Compositional Reasoning on Vision and Commonsense | DIFEI GAO et. al. | In this paper, we introduce a VQA dataset that provides more challenging and general questions about Compositional Reasoning on vIsion and Commonsense, which is named as CRIC. | CS.arxiv | 2019-08-08 |
| 565 | Question-Agnostic Attention for Visual Question Answering | MOSHIUR R FARAZI et. al. | In this paper, we propose a question-agnostic attention mechanism that is complementary to the existing question-dependent attention mechanisms. | CS.arxiv | 2019-08-08 |
| 566 | Mitigating Noisy Inputs for Question Answering | DENIS PESKOV et. al. | We create and train models on a synthetic corpus of over 500,000 noisy sentences and evaluate on two human corpora from Quizbowl and Jeopardy! competitions. | CS.arxiv | 2019-08-07 |
| 567 | Answering Questions about Data Visualizations using Efficient Bimodal Fusion | KUSHAL KAFLE et. al. | Here, we propose a novel CQA algorithm called parallel recurrent fusion of image and language (PReFIL). | CS.arxiv | 2019-08-05 |
| 568 | Walking with MIND: Mental Imagery eNhanceD Embodied QA | JUNCHENG LI et. al. | In this paper, we propose a novel Mental Imagery eNhanceD (MIND) module for the embodied agent, as well as a relevant deep reinforcement framework for training. | CS.arxiv | 2019-08-05 |
| 569 | Exploring Neural Net Augmentation to BERT for Question Answering on SQUAD 2.0 | SUHAS GUPTA | In this work, we focused on augmenting the pre-trained BERT language model with different output neural net architectures and compared their performance on question answering task posed by the Stanford Question Answering Dataset 2.0 (SQUAD 2.0) [3]. | CS.arxiv | 2019-08-04 |
| 570 | Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphs | XIAOLU LU et. al. | This paper presents QUEST, a method that can answer complex questions directly from textual sources on-the-fly, by computing similarity joins over partial results from different documents. | CS.arxiv | 2019-08-01 |
| 571 | Deep Bayesian Mining, Learning and Understanding | JEN-TZUNG CHIEN | We present how these models are connected and why they work for a variety of applications on symbolic and complex patterns in natural language. | CS.kdd | 2019-08-01 |
| 572 | Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks | NAMYONG PARK et. al. | In this paper, we present GENI, a method for tackling the problem of estimating node importance in KGs, which enables several downstream applications such as item recommendation and resource allocation. | CS.kdd | 2019-08-01 |
| 573 | Integrating Domain-Knowledge into Deep Learning | RUSLAN SALAKHUTDINOV | I will present a modular hierarchical reinforcement learning agent that can learn to store arbitrary information about the environment over long time lags, perform efficient exploration and long-term planning, while generalizing across domains and tasks. | CS.kdd | 2019-08-01 |
| 574 | Learning Dynamic Context Graphs for Predicting Social Events | SONGGAOJUN DENG et. al. | In this paper, we study graph representations in modeling social events to identify dynamic properties of event contexts as social indicators. | CS.kdd | 2019-08-01 |
| 575 | Naranjo Question Answering using End-to-End Multi-task Learning Model | BHANU PRATAP SINGH RAWAT et. al. | In this study, we present the first attempt to automatically infer the causality between a drug and an ADR from electronic health records (EHRs) by answering the Naranjo questionnaire, the validated clinical question answering set used by domain experts for ADR causality assessment. | CS.kdd | 2019-08-01 |
| 576 | Riker: Mining Rich Keyword Representations for Interpretable Product Question Answering | JIE ZHAO et. al. | In this work, we develop a new PQA framework (named Riker) that enjoys the benefits of both interpretability and effectiveness. | CS.kdd | 2019-08-01 |
| 577 | Spinning the AI Pinwheel | JAIRAM RANGANATHAN | This paper describes a general structure for accelerating the annotation process using artificial intelligence and combining it with model quality assurance (QA). | CS.kdd | 2019-08-01 |
| 578 | TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank | RAMA KUMAR PASUMARTHI et. al. | We introduce TensorFlow Ranking, the first open source library for solving large-scale ranking problems in a deep learning framework. | CS.kdd | 2019-08-01 |
| 579 | An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation | VINCENT MICHALSKI et. al. | In this work, we study whether and where the conditional formulation of group normalization can improve generalization compared to conditional batch normalization. | CS.arxiv | 2019-07-31 |
| 580 | LEAF-QA: Locate, Encode & Attend for Figure Question Answering | RITWICK CHAUDHRY et. al. | We introduce LEAF-QA, a comprehensive dataset of $250,000$ densely annotated figures/charts, constructed from real-world open data sources, along with ~2 million question-answer (QA) pairs querying the structure and semantics of these charts. | CS.arxiv | 2019-07-30 |
| 581 | Learning Question-Guided Video Representation for Multi-Turn Video Question Answering | GUAN-LIN CHAO et. al. | Through empirical evaluation on the Audio Visual Scene-aware Dialog (AVSD) dataset, our proposed models in single-turn and multi-turn question answering achieve state-of-the-art performance on several automatic natural language generation evaluation metrics. | CS.arxiv | 2019-07-30 |
| 582 | A mathematical model for universal semantics | WEINAN E et. al. | We characterize the meaning of words with language-independent numerical fingerprints, through a mathematical analysis of recurring patterns in texts. | CS.arxiv | 2019-07-29 |
| 583 | Reinforced Dynamic Reasoning for Conversational Question Generation | BOYUAN PAN et. al. | Towards that end, we propose a new approach named Reinforced Dynamic Reasoning (ReDR) network, which is based on the general encoder-decoder framework but incorporates a reasoning procedure in a dynamic manner to better understand what has been asked and what to ask next about the passage. | CS.arxiv | 2019-07-29 |
| 584 | An Empirical Study on Leveraging Scene Graphs for Visual Question Answering | CHENG ZHANG et. al. | In this paper, we investigate an alternative approach inspired by conventional QA systems that operate on knowledge graphs. | CS.arxiv | 2019-07-28 |
| 585 | Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction | KOSUKE NISHIDA et. al. | This study focuses on the task of explainable multi-hop QA, which requires the system to return the answer with evidence sentences by reasoning and gathering disjoint pieces of the reference texts. | CS.acl | 2019-07-28 |
| 586 | Are Red Roses Red? Evaluating Consistency of Question-Answering Models | MARCO TULIO RIBEIRO et. al. | We propose a method to automatically extract such implications for instances from two QA datasets, VQA and SQuAD, which we then use to evaluate the consistency of models. | CS.acl | 2019-07-28 |
| 587 | Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network | JINGJING WANG et. al. | This paper extends the research to interactive reviews and proposes a new research task, namely Aspect Sentiment Classification towards Question-Answering (ASC-QA), for real-world applications. | CS.acl | 2019-07-28 |
| 588 | Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA | YICHEN JIANG et. al. | In this paper, we show that in the multi-hop HotpotQA (Yang et al., 2018) dataset, the examples often contain reasoning shortcuts through which models can directly locate the answer by word-matching the question with a sentence in the context. | CS.acl | 2019-07-28 |
| 589 | Careful Selection of Knowledge to Solve Open Book Question Answering | PRATYAY BANERJEE et. al. | In this paper we address QA with respect to the OpenBookQA dataset and combine state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection and weighted scoring to achieve 72.0% accuracy, an 11.6% improvement over the current state of the art. | CS.acl | 2019-07-28 |
| 590 | Cognitive Graph for Multi-Hop Reading Comprehension at Scale | MING DING et. al. | We propose a new CogQA framework for multi-hop reading comprehension question answering in web-scale documents. | CS.acl | 2019-07-28 |
| 591 | Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading | LIANHUI QIN et. al. | We present a new end-to-end approach to contentful neural conversation that jointly models response generation and on-demand machine reading. To support further research on knowledge-grounded conversation, we introduce a new large-scale conversation dataset grounded in external web pages (2.8M turns, 7.4M sentences of grounding). | CS.acl | 2019-07-28 |
| 592 | Cross-Lingual Training for Automatic Question Generation | VISHWAJEET KUMAR et. al. | We propose a cross-lingual QG model which uses the following training regime: (i) Unsupervised pretraining of language models in both primary and secondary languages and (ii) joint supervised training for QG in both languages. | CS.acl | 2019-07-28 |
| 593 | Do You Know That Florence Is Packed with Visitors? Evaluating State-of-the-art Models of Speaker Commitment | NANJIANG JIANG et. al. | Here, we explore the hypothesis that linguistic deficits drive the error patterns of existing speaker commitment models by analyzing the linguistic correlates of model error on a challenging naturalistic dataset. | CS.acl | 2019-07-28 |
| 594 | Dynamically Fused Graph Network for Multi-hop Reasoning | LIN QIU et. al. | In this paper, we propose Dynamically Fused Graph Network (DFGN), a novel method to answer those questions requiring multiple scattered evidence and reasoning over them. | CS.acl | 2019-07-28 |
| 595 | ELI5: Long Form Question Answering | ANGELA FAN et. al. | We introduce the first large-scale corpus for long form question answering, a task requiring elaborate and in-depth answers to open-ended questions. | CS.acl | 2019-07-28 |
| 596 | Entity-Relation Extraction as Multi-Turn Question Answering | XIAOYA LI et. al. | In this paper, we propose a new paradigm for the task of entity-relation extraction. | CS.acl | 2019-07-28 |
| 597 | Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data | MOONSU HAN et. al. | To tackle this problem, we propose a novel end-to-end deep network model for reading comprehension, which we refer to as Episodic Memory Reader (EMR) that sequentially reads the input contexts into an external memory, while replacing memories that are less important for answering unseen questions. | CS.acl | 2019-07-28 |
| 598 | Generating Question Relevant Captions to Aid Visual Question Answering | JIALIN WU et. al. | We present a novel approach to better VQA performance that exploits this connection by jointly generating captions that are targeted to help answer a specific visual question. | CS.acl | 2019-07-28 |
| 599 | Generating Question-Answer Hierarchies | KALPESH KRISHNA et. al. | In this paper, we present SQUASH (Specificity-controlled Question-Answer Hierarchies), a novel and challenging text generation task that converts an input document into a hierarchy of question-answer pairs. | CS.acl | 2019-07-28 |
| 600 | HEAD-QA: A Healthcare Dataset for Complex Reasoning | DAVID VILARES et. al. | We present HEAD-QA, a multi-choice question answering testbed to encourage research on complex reasoning. | CS.acl | 2019-07-28 |
| 601 | Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader | WENHAN XIONG et. al. | We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets.Under the assumptions that structured data is easier to query and the acquired knowledge can help the understanding of unstructured text, our model first accumulates knowledge ofKB entities from a question-related KB sub-graph; then reformulates the question in the latent space and reads the text with the accumulated entity knowledge at hand. | CS.acl | 2019-07-28 |
| 602 | Improving the Robustness of Question Answering Systems to Question Paraphrasing | WEE CHUNG GAN et. al. | Using a neural paraphrasing model trained to generate multiple paraphrased questions for a given source question and a set of paraphrase suggestions, we propose a data augmentation approach that requires no human intervention to re-train the models for improved robustness to question paraphrasing. | CS.acl | 2019-07-28 |
| 603 | Improving Visual Question Answering by Referring to Generated Paragraph Captions | HYOUNGHUN KIM et. al. | Hence, we propose a combined Visual and Textual Question Answering (VTQA) model which takes as input a paragraph caption as well as the corresponding image, and answers the given question based on both inputs. | CS.acl | 2019-07-28 |
| 604 | Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling | YIFAN GAO et. al. | We propose an end-to-end neural model with coreference alignment and conversation flow modeling. | CS.acl | 2019-07-28 |
| 605 | Interpretable Question Answering on Knowledge Bases and Text | ALONA SYDOROVA et. al. | In this work, we address the interpretability of ML based question answering (QA) models on a combination of knowledge bases (KB) and text documents. | CS.acl | 2019-07-28 |
| 606 | Latent Retrieval for Weakly Supervised Open Domain Question Answering | KENTON LEE et. al. | We show for the first time that it is possible to jointly learn the retriever and reader from question-answer string pairs and without any IR system. | CS.acl | 2019-07-28 |
| 607 | Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering | PENG WU et. al. | In this paper, we propose a simple mapping method, named representation adapter, to learn the representation mapping for both seen and unseen relations based on previously learned relation embedding. | CS.acl | 2019-07-28 |
| 608 | Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization | PAUL PU LIANG et. al. | To address these concerns, we present a regularization method based on tensor rank minimization. | CS.acl | 2019-07-28 |
| 609 | MC^2: Multi-perspective Convolutional Cube for Conversational Machine Reading Comprehension | XUANYU ZHANG, | To comprehend context profoundly and efficiently from different perspectives, we propose a novel neural network model, Multi-perspective Convolutional Cube (MC{\^{}}2). | CS.acl | 2019-07-28 |
| 610 | Multi-grained Attention with Object-level Grounding for Visual Question Answering | PINGPING HUANG et. al. | To address this problem, this paper proposes a multi-grained attention method. | CS.acl | 2019-07-28 |
| 611 | Multi-Hop Paragraph Retrieval for Open-Domain Question Answering | YAIR FELDMAN et. al. | We present a method for retrieving multiple supporting paragraphs, nested amidst a large knowledge base, which contain the necessary evidence to answer a given question. | CS.acl | 2019-07-28 |
| 612 | Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog | ZHE GAN et. al. | This paper presents a new model for visual dialog, Recurrent Dual Attention Network (ReDAN), using multi-step reasoning to answer a series of questions about an image. | CS.acl | 2019-07-28 |
| 613 | Multi-style Generative Reading Comprehension | KYOSUKE NISHIDA et. al. | We propose a multi-style abstractive summarization model for question answering, called Masque. | CS.acl | 2019-07-28 |
| 614 | NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language | LEON WEBER et. al. | In this paper, we describe a model combining neural networks with logic programming in a novel manner for solving multi-hop reasoning tasks over natural language. | CS.acl | 2019-07-28 |
| 615 | On the Summarization of Consumer Health Questions | ASMA BEN ABACHA et. al. | In this paper, we study neural abstractive models for medical question summarization. | CS.acl | 2019-07-28 |
| 616 | Open-Domain Why-Question Answering with Adversarial Learning to Encode Answer Texts | JONG-HOON OH et. al. | In this paper, we propose a method for why-question answering (why-QA) that uses an adversarial learning framework. | CS.acl | 2019-07-28 |
| 617 | Psycholinguistics Meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering | CLAUDIO GRECO et. al. | We study the issue of catastrophic forgetting in the context of neural multimodal approaches to Visual Question Answering (VQA). | CS.acl | 2019-07-28 |
| 618 | RankQA: Neural Question Answering with Answer Re-Ranking | BERNHARD KRATZWALD et. al. | In contrast, this work proposes RankQA: RankQA extends the conventional two-stage process in neural QA with a third stage that performs an additional answer re-ranking. | CS.acl | 2019-07-28 |
| 619 | Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index | MINJOON SEO et. al. | In this paper, we introduce query-agnostic indexable representations of document phrases that can drastically speed up open-domain QA. | CS.acl | 2019-07-28 |
| 620 | Reinforced Dynamic Reasoning for Conversational Question Generation | BOYUAN PAN et. al. | Towards that end, we propose a new approach named Reinforced Dynamic Reasoning network, which is based on the general encoder-decoder framework but incorporates a reasoning procedure in a dynamic manner to better understand what has been asked and what to ask next about the passage into the general encoder-decoder framework. | CS.acl | 2019-07-28 |
| 621 | Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension | MINGHAO HU et. al. | In this work, we present RE$^3$QA, a unified question answering model that combines context retrieving, reading comprehension, and answer reranking to predict the final answer. | CS.acl | 2019-07-28 |
| 622 | Synthetic QA Corpora Generation with Roundtrip Consistency | CHRIS ALBERTI et. al. | We introduce a novel method of generating synthetic question answering corpora by combining models of question generation and answer extraction, and by filtering the results to ensure roundtrip consistency. | CS.acl | 2019-07-28 |
| 623 | 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.arxiv | 2019-07-28 |
| 624 | Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension | DAESIK KIM et. al. | In this work, we introduce a novel algorithm for solving the textbook question answering (TQA) task which describes more realistic QA problems compared to other recent tasks. | CS.acl | 2019-07-28 |
| 625 | Towards Automating Healthcare Question Answering in a Noisy Multilingual Low-Resource Setting | JEANNE E. DANIEL et. al. | We discuss ongoing work into automating amultilingual digital helpdesk service availablevia text messaging to pregnant and breastfeed-ing mothers in South Africa. | CS.acl | 2019-07-28 |
| 626 | Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications | WEI ZHAO et. al. | In this paper, we introduce: (i) an agreement score to evaluate the performance of routing processes at instance-level; (ii) an adaptive optimizer to enhance the reliability of routing; (iii) capsule compression and partial routing to improve the scalability of capsule networks. | CS.acl | 2019-07-28 |
| 627 | TWEETQA: A Social Media Focused Question Answering Dataset | WENHAN XIONG et. al. | While previous datasets have concentrated on question answering (QA) for formal text like news and Wikipedia, we present the first large-scale dataset for QA over social media data. | CS.acl | 2019-07-28 |
| 628 | Unsupervised Question Answering by Cloze Translation | PATRICK LEWIS et. al. | In this work, we explore to what extent high quality training data is actually required for Extractive QA, and investigate the possibility of unsupervised Extractive QA. | CS.acl | 2019-07-28 |
| 629 | XQA: A Cross-lingual Open-domain Question Answering Dataset | JIAHUA LIU et. al. | In this paper, we construct a novel dataset XQA for cross-lingual OpenQA research. | CS.acl | 2019-07-28 |
| 630 | Careful Selection of Knowledge to solve Open Book Question Answering | PRATYAY BANERJEE et. al. | In this paper we address QA with respect to the OpenBookQA dataset and combine state of the art language models with abductive information retrieval (IR), information gain based re-ranking, passage selection and weighted scoring to achieve 72.0% accuracy, an 11.6% improvement over the current state of the art. | CS.arxiv | 2019-07-24 |
| 631 | SpanBERT: Improving Pre-training by Representing and Predicting Spans | MANDAR JOSHI et. al. | We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. | CS.arxiv | 2019-07-24 |
| 632 | Bilinear Graph Networks for Visual Question Answering | DALU GUO et. al. | In contrast, we develop bilinear graph networks to model the context of the joint embeddings of words and objects. | CS.arxiv | 2019-07-23 |
| 633 | Metalearned Neural Memory | TSENDSUREN MUNKHDALAI et. al. | The proposed memory-augmented model achieves strong performance on a variety of learning problems, from supervised question answering to reinforcement learning. | CS.arxiv | 2019-07-23 |
| 634 | ELI5: Long Form Question Answering | ANGELA FAN et. al. | We introduce the first large-scale corpus for long-form question answering, a task requiring elaborate and in-depth answers to open-ended questions. We provide a large set of web documents to help answer the question. | CS.arxiv | 2019-07-22 |
| 635 | Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs | NILESH CHAKRABORTY et. al. | Through this article, we aim to provide newcomers to the field with a suitable entry point, and ease their process of making informed decisions while creating their own QA system. | CS.arxiv | 2019-07-22 |
| 636 | Adaptive Multi-Attention Network Incorporating Answer Information for Duplicate Question Detection | DI LIANG et. al. | In this paper, we propose an answer information- enhanced adaptive multi-attention network (AMAN) to perform this task. | CS.sigir | 2019-07-20 |
| 637 | Answer-enhanced Path-aware Relation Detection over Knowledge Base | DAOYUAN CHEN et. al. | In this paper, we propose a Knowledge-driven Relation Detection network (KRD) to interactively learn answer-enhanced question representations and path-aware relation representations for relation detection. | CS.sigir | 2019-07-20 |
| 638 | Controlling Risk of Web Question Answering | LIXIN SU et. al. | In this work, we first conduct an in-depth investigation over the risk of Web QA. We then introduce a novel risk control framework, which consists of a qualify model for uncertainty estimation using the probe idea, and a decision model for selectively output. | CS.sigir | 2019-07-20 |
| 639 | Document Gated Reader for Open-Domain Question Answering | BINGNING WANG et. al. | In this paper, we propose a document gated reader to generate the right answer from multiple documents. | CS.sigir | 2019-07-20 |
| 640 | Evaluating Variable-Length Multiple-Option Lists in Chatbots and Mobile Search | PEPA ATANASOVA et. al. | How to produce good variable-length lists, given the conflicting objectives of staying short while maximizing the likelihood of having a correct answer included in the list, is an underexplored problem. It is also unclear how to evaluate a system that tries to do that. Here we aim to bridge this gap. | CS.sigir | 2019-07-20 |
| 641 | Explanatory and Actionable Debugging for Machine Learning: A TableQA Demonstration | MINSEOK CHO et. al. | The goal of this demonstration is to show a debugging tool for such models, explaining answers to humans, known as explanatory debugging. | CS.sigir | 2019-07-20 |
| 642 | FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevance | WATARU SAKATA et. al. | We propose a FAQ retrieval system that considers the similarity between a user’s query and a question as well as the relevance between the query and an answer. | CS.sigir | 2019-07-20 |
| 643 | How to Deal with Scarce Annotations in Answer Selection | EMMANUEL VALLEE et. al. | In this work, we are interested in simple models that can potentially give good performance on datasets with no or few annotations. | CS.sigir | 2019-07-20 |
| 644 | Multi-Level Matching Networks for Text Matching | CHUNLIN XU et. al. | Therefore, instead of making decisions utilizing single level word representations, a multi-level matching network (MMN) is proposed in this paper for text matching, which utilizes multiple levels of word representations to obtain multiple word level matching results for final text level matching decision. | CS.sigir | 2019-07-20 |
| 645 | Non-factoid Question Answering in the Legal Domain | GAYLE MCELVAIN et. al. | We present work done on a QA system that is entirely based on IR and NLP, and does not rely on a structured knowledge base. | CS.sigir | 2019-07-20 |
| 646 | Quantifying and Alleviating the Language Prior Problem in Visual Question Answering | YANGYANG GUO et. al. | In this paper, we make contributions to solve the above problems from two perspectives. | CS.sigir | 2019-07-20 |
| 647 | The Importance of Interaction for Information Retrieval | W. BRUCE CROFT | I will describe the specific lines of research we have followed at the Center for Intelligent Information Retrieval and RMIT, including interactive answer passage retrieval, studies of information-seeking dialogues, and neural models for selecting responses and answers. | CS.sigir | 2019-07-20 |
| 648 | Web Table Extraction, Retrieval and Augmentation | SHUO ZHANG et. al. | This tutorial synthesizes and presents research on web tables over the past two decades. | CS.sigir | 2019-07-20 |
| 649 | WestSearch Plus: A Non-factoid Question-Answering System for the Legal Domain | GAYLE MCELVAIN et. al. | We present a non-factoid QA system that provides legally accurate, jurisdictionally relevant, and conversationally responsive answers to user-entered questions in the legal domain. | CS.sigir | 2019- |