Predicting Depression in Screening Interviews from Latent Categorization of Interview Prompts Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling Designing Precise and Robust Dialogue Response Evaluators PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking A Complete Shift-Reduce Chinese Discourse Parser with Robust Dynamic Oracle Few-Shot NLG with Pre-Trained Language Model Fluent Response Generation for Conversational Question Answering Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs Neural Syntactic Preordering for Controlled Paraphrase Generation Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders Unsupervised Paraphrasing by Simulated Annealing Contextualized Weak Supervision for Text Classification Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks Jointly Masked Sequence-to-Sequence Model for Non-Autoregressive Neural Machine Translation Norm-Based Curriculum Learning for Neural Machine Translation A Formal Hierarchy of RNN Architectures GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2 Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition Paraphrase Augmented Task-Oriented Dialog Generation Towards Unsupervised Language Understanding and Generation by Joint Dual Learning Improved Natural Language Generation via Loss Truncation Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks Rigid Formats Controlled Text Generation Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation An Online Semantic-enhanced Dirichlet Model for Short Text Stream Clustering Tree-Structured Neural Topic Model Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check A Methodology for Creating Question Answering Corpora Using Inverse Data Annotation Contextualized Sparse Representations for Real-Time Open-Domain Question Answering Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading Injecting Numerical Reasoning Skills into Language Models Learning to Identify Follow-Up Questions in Conversational Question Answering Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases Improving Image Captioning Evaluation by Considering Inter References Variance Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders Towards Conversational Recommendation over Multi-Type Dialogs Exclusive Hierarchical Decoding for Deep Keyphrase Generation Hierarchy-Aware Global Model for Hierarchical Text Classification A Graph Auto-encoder Model of Derivational Morphology Crawling and Preprocessing Mailing Lists At Scale for Dialog Analysis Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences Multi-Hypothesis Machine Translation Evaluation PuzzLing Machines: A Challenge on Learning From Small Data The SOFC-Exp Corpus and Neural Approaches to Information Extraction in the Materials Science Domain iSarcasm: A Dataset of Intended Sarcasm AMR Parsing via Graph-Sequence Iterative Inference A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal Attend, Translate and Summarize: An Efficient Method for Neural Cross-Lingual Summarization SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation Conversational Word Embedding for Retrieval-Based Dialog System Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network MuTual: A Dataset for Multi-Turn Dialogue Reasoning You Impress Me: Dialogue Generation via Mutual Persona Perception Bridging Anaphora Resolution as Question Answering Dialogue Coherence Assessment Without Explicit Dialogue Act Labels Semantic Graphs for Generating Deep Questions
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction
In Layman’s Terms: Semi-Open Relation Extraction from Scientific Texts
NAT: Noise-Aware Training for Robust Neural Sequence Labeling Named Entity Recognition without Labelled Data: A Weak Supervision Approach
Reasoning with Latent Structure Refinement for Document-Level Relation Extraction
TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task
Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences Character-Level Translation with Self-attention Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation It’s Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation
Will-They-Won’t-They: A Very Large Dataset for Stance Detection on Twitter
A Systematic Assessment of Syntactic Generalization in Neural Language Models Suspense in Short Stories is Predicted By Uncertainty Reduction over Neural Story Representation You Don’t Have Time to Read This: An Exploration of Document Reading Time Prediction GPT-too: A Language-Model-First Approach for AMR-to-Text Generation
Learning to Update Natural Language Comments Based on Code Changes
Politeness Transfer: A Tag and Generate Approach On Faithfulness and Factuality in Abstractive Summarization Screenplay Summarization Using Latent Narrative Structure Unsupervised Opinion Summarization with Noising and Denoising Probing Linguistic Systematicity Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment What determines the order of adjectives in English? Comparing efficiency-based theories using dependency treebanks Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs Negative Training for Neural Dialogue Response Generation Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback Calibrating Structured Output Predictors for Natural Language Processing Active Imitation Learning with Noisy Guidance ExpBERT: Representation Engineering with Natural Language Explanations GAN-BERT: Generative Adversarial Learning for Robust Text Classification with a Bunch of Labeled Examples Generalizing Natural Language Analysis through Span-relation Representations Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices Taxonomy Construction of Unseen Domains via Graph-based Cross-Domain Knowledge Transfer Why Overfitting Isn’t Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries XtremeDistil: Multi-stage Distillation for Massive Multilingual Models A Girl Has A Name: Detecting Authorship Obfuscation DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference Investigating the effect of auxiliary objectives for the automated grading of learner English speech transcriptions SPECTER: Document-level Representation Learning using Citation-informed Transformers Semantic Scaffolds for Pseudocode-to-Code Generation INFOTABS: Inference on Tables as Semi-structured Data Interactive Machine Comprehension with Information Seeking Agents Syntactic Data Augmentation Increases Robustness to Inference Heuristics Grounding Conversations with Improvised Dialogues Learning an Unreferenced Metric for Online Dialogue Evaluation Neural Generation of Dialogue Response Timings The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents Automatic Poetry Generation from Prosaic Text Enabling Language Models to Fill in the Blanks INSET: Sentence Infilling with INter-SEntential Transformer BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps
Cross-media Structured Common Space for Multimedia Event Extraction
MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning What is Learned in Visually Grounded Neural Syntax Acquisition A Batch Normalized Inference Network Keeps the KL Vanishing Away Contextual Embeddings: When Are They Worth It? Interactive Classification by Asking Informative Questions Low Resource Sequence Tagging using Sentence Reconstruction Masked Language Model Scoring Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding Posterior Calibrated Training on Sentence Classification Tasks Posterior Control of Blackbox Generation Pretrained Transformers Improve Out-of-Distribution Robustness Robust Encodings: A Framework for Combating Adversarial Typos Showing Your Work Doesn’t Always Work Topological Sort for Sentence Ordering Weight Poisoning Attacks on Pretrained Models ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation Verbal Multiword Expressions for Identification of Metaphor It’s Morphin’ Time! Combating Linguistic Discrimination with Inflectional Perturbations How Does Selective Mechanism Improve Self-Attention Networks? Improving Transformer Models by Reordering their Sublayers Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation Geometry-aware domain adaptation for unsupervised alignment of word embeddings Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation On the Inference Calibration of Neural Machine Translation Camouflaged Chinese Spam Content Detection with Semi-supervised Generative Active Learning Distinguish Confusing Law Articles for Legal Judgment Prediction Hiring Now: A Skill-Aware Multi-Attention Model for Job Posting Generation MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs Analyzing the Persuasive Effect of Style in News Editorial Argumentation
Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair Extraction
Embarrassingly Simple Unsupervised Aspect Extraction
KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis Relational Graph Attention Network for Aspect-based Sentiment Analysis A Span-based Linearization for Constituent Trees An Empirical Comparison of Unsupervised Constituency Parsing Methods Efficient Constituency Parsing by Pointing Efficient Second-Order TreeCRF for Neural Dependency Parsing Representations of Syntax [MASK] Useful: Effects of Constituency and Dependency Structure in Recursive LSTMs Structure-Level Knowledge Distillation For Multilingual Sequence Labeling Dynamic Online Conversation Recommendation An Analysis of the Utility of Explicit Negative Examples to Improve the Syntactic Abilities of Neural Language Models On the Robustness of Language Encoders against Grammatical Errors Roles and Utilization of Attention Heads in Transformer-based Neural Language Models Understanding Attention for Text Classification A Relational Memory-based Embedding Model for Triple Classification and Search Personalization Do you have the right scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions A Retrieve-and-Rewrite Initialization Method for Unsupervised Machine Translation Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation Lexically Constrained Neural Machine Translation with Levenshtein Transformer On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation ChartDialogs: Plotting from Natural Language Instructions MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization That is a Known Lie: Detecting Previously Fact-Checked Claims Towards Holistic and Automatic Evaluation of Open-Domain Dialogue Generation Biomedical Entity Representations with Synonym Marginalization Hypernymy Detection for Low-Resource Languages via Meta Learning Relation-Aware Collaborative Learning for Unified Aspect-Based Sentiment Analysis SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics
Transition-based Directed Graph Construction for Emotion-Cause Pair Extraction
CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotation of Modality How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems Improving Disfluency Detection by Self-Training a Self-Attentive Model Learning Spoken Language Representations with Neural Lattice Language Modeling Meta-Transfer Learning for Code-Switched Speech Recognition Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data SEEK: Segmented Embedding of Knowledge Graphs Graph-to-Tree Learning for Solving Math Word Problems Analysing Lexical Semantic Change with Contextualised Word Representations BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance CluBERT: A Cluster-Based Approach for Learning Sense Distributions in Multiple Languages GoEmotions: A Dataset of Fine-Grained Emotions SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis Enriched In-Order Linearization for Faster Sequence-to-Sequence Constituent Parsing Max-Margin Incremental CCG Parsing Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting Analyzing analytical methods: The case of phonology in neural models of spoken language Quantifying Attention Flow in Transformers Towards Transparent and Explainable Attention Models Empowering Active Learning to Jointly Optimize System and User Demands Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction Toxicity Detection: Does Context Really Matter? AMR Parsing with Latent Structural Information TaPas: Weakly Supervised Table Parsing via Pre-training Target Inference in Argument Conclusion Generation Sentiment and Emotion help Sarcasm? A Multi-task Learning Framework for Multi-Modal Sarcasm, Sentiment and Emotion Analysis Towards Emotion-aided Multi-modal Dialogue Act Classification Analyzing Political Parody in Social Media When do Word Embeddings Accurately Reflect Surveys on our Beliefs About People? Compositionality and Generalization In Emergent Languages ERASER: A Benchmark to Evaluate Rationalized NLP Models Learning to Faithfully Rationalize by Construction Clinical Reading Comprehension: A Thorough Analysis of the emrQA Dataset DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering A Corpus for Large-Scale Phonetic Typology Dscorer: A Fast Evaluation Metric for Discourse Representation Structure Parsing Information-Theoretic Probing for Linguistic Structure On the Cross-lingual Transferability of Monolingual Representations Similarity Analysis of Contextual Word Representation Models Fatality Killed the Cat or: BabelPic, a Multimodal Dataset for Non-Concrete Concepts Modeling Label Semantics for Predicting Emotional Reactions Don’t Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training How does BERT’s attention change when you fine-tune? An analysis methodology and a case study in negation scope Interpreting Pretrained Contextualized Representations via Reductions to Static Embeddings Learning to Deceive with Attention-Based Explanations On the Spontaneous Emergence of Discrete and Compositional Signals Spying on your neighbors: Fine-grained probing of contextual embeddings for information about surrounding words Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA Shaping Visual Representations with Language for Few-Shot Classification Discrete Latent Variable Representations for Low-Resource Text Classification Learning Constraints for Structured Prediction Using Rectifier Networks Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks Beyond Accuracy: Behavioral Testing of NLP Models with CheckList Code and Named Entity Recognition in StackOverflow
Dialogue-Based Relation Extraction
Facet-Aware Evaluation for Extractive Summarization
S2ORC: The Semantic Scholar Open Research Corpus Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics A Transformer-based Approach for Source Code Summarization Asking and Answering Questions to Evaluate the Factual Consistency of Summaries
Discourse-Aware Neural Extractive Text Summarization
Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction
Exploring Content Selection in Summarization of Novel Chapters FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization Fact-based Content Weighting for Evaluating Abstractive Summarisation Hooks in the Headline: Learning to Generate Headlines with Controlled Styles Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward The Summary Loop: Learning to Write Abstractive Summaries Without Examples Unsupervised Opinion Summarization as Copycat-Review Generation How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence What Does BERT with Vision Look At? Balancing Objectives in Counseling Conversations: Advancing Forwards or Looking Backwards Detecting Perceived Emotions in Hurricane Disasters Measuring Forecasting Skill from Text Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event Harnessing the linguistic signal to predict scalar inferences PeTra: A Sparsely Supervised Memory Model for People Tracking ZPR2: Joint Zero Pronoun Recovery and Resolution using Multi-Task Learning and BERT Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation Towards Debiasing Sentence Representations A Re-evaluation of Knowledge Graph Completion Methods Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior? Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions Finding Universal Grammatical Relations in Multilingual BERT Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection Obtaining Faithful Interpretations from Compositional Neural Networks Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport Benefits of Intermediate Annotations in Reading Comprehension Logic-Guided Data Augmentation and Regularization for Consistent Question Answering Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations Selective Question Answering under Domain Shift The Cascade Transformer: an Application for Efficient Answer Sentence Selection Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering Not All Claims are Created Equal: Choosing the Right Statistical Approach to Assess Hypotheses STARC: Structured Annotations for Reading Comprehension WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge Cross-Lingual Unsupervised Sentiment Classification with Multi-View Transfer Learning Efficient Pairwise Annotation of Argument Quality OpinionDigest: A Simple Framework for Opinion Summarization A Comprehensive Analysis of Preprocessing for Word Representation Learning in Affective Tasks Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks A Unified MRC Framework for Named Entity Recognition An Effective Transition-based Model for Discontinuous NER
IMoJIE: Iterative Memory-Based Joint Open Information Extraction
Improving Event Detection via Open-domain Trigger Knowledge Multi-Cell Compositional LSTM for NER Domain Adaptation ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph Embedding Simplify the Usage of Lexicon in Chinese NER Contextual Neural Machine Translation Improves Translation of Cataphoric Pronouns FastBERT: a Self-distilling BERT with Adaptive Inference Time Incorporating External Knowledge through Pre-training for Natural Language to Code Generation Word-level Textual Adversarial Attacking as Combinatorial Optimization Benchmarking Multimodal Regex Synthesis with Complex Structures Do Neural Models Learn Systematicity of Monotonicity Inference in Natural Language? Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder Automatic Generation of Citation Texts in Scholarly Papers: A Pilot Study Composing Elementary Discourse Units in Abstractive Summarization
Extractive Summarization as Text Matching
Heterogeneous Graph Neural Networks for Extractive Document Summarization
Leveraging Graph to Improve Abstractive Multi-Document Summarization Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog Speaker Sensitive Response Evaluation Model Amalgamation of protein sequence, structure and textual information for improving protein-protein interaction identification Bipartite Flat-Graph Network for Nested Named Entity Recognition Connecting Embeddings for Knowledge Graph Entity Typing Continual Relation Learning via Episodic Memory Activation and Reconsolidation Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition
MIE: A Medical Information Extractor towards Medical Dialogues
Named Entity Recognition as Dependency Parsing Cross-modal Coherence Modeling for Caption Generation Knowledge Supports Visual Language Grounding: A Case Study on Colour Terms Span-based Localizing Network for Natural Language Video Localization Words Aren’t Enough, Their Order Matters: On the Robustness of Grounding Visual Referring Expressions A Mixture of h - 1 Heads is Better than h Heads Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification Differentiable Window for Dynamic Local Attention Evaluating and Enhancing the Robustness of Neural Network-based Dependency Parsing Models with Adversarial Examples Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation Modeling Morphological Typology for Unsupervised Learning of Language Morphology Predicting Declension Class from Form and Meaning Unsupervised Morphological Paradigm Completion Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension Harvesting and Refining Question-Answer Pairs for Unsupervised QA R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension Parsing into Variable-in-situ Logico-Semantic Graphs Semi-Supervised Semantic Dependency Parsing Using CRF Autoencoders DRTS Parsing with Structure-Aware Encoding and Decoding A Two-Stage Masked LM Method for Term Set Expansion FLAT: Chinese NER Using Flat-Lattice Transformer Improving Entity Linking through Semantic Reinforced Entity Embeddings Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing Highway Transformer: Self-Gating Enhanced Self-Attentive Networks Low-Dimensional Hyperbolic Knowledge Graph Embeddings Classification-Based Self-Learning for Weakly Supervised Bilingual Lexicon Induction Uncertainty-Aware Curriculum Learning for Neural Machine Translation Closing the Gap: Joint De-Identification and Concept Extraction in the Clinical Domain From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains Language to Network: Conditional Parameter Adaptation with Natural Language Descriptions Controlled Crowdsourcing for High-Quality QA-SRL Annotation Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpus Transition-based Semantic Dependency Parsing with Pointer Networks tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection Exploiting Personal Characteristics of Debaters for Predicting Persuasiveness Diversifying Dialogue Generation with Non-Conversational Text KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation Multi-Domain Dialogue Acts and Response Co-Generation Heterogeneous Graph Transformer for Graph-to-Sequence Learning Refer360: A Referring Expression Recognition Dataset in 360 Images CamemBERT: a Tasty French Language Model Effective Estimation of Deep Generative Language Models Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection 2kenize: Tying Subword Sequences for Chinese Script Conversion Predicting the Growth of Morphological Families from Social and Linguistic Factors Semi-supervised Contextual Historical Text Normalization ClarQ: A large-scale and diverse dataset for Clarification Question Generation
MLQA: Evaluating Cross-lingual Extractive Question Answering
Fine-grained Fact Verification with Kernel Graph Attention Network Premise Selection in Natural Language Mathematical Texts Improving Image Captioning with Better Use of Caption Toward Better Storylines with Sentence-Level Language Models A Two-Step Approach for Implicit Event Argument Detection Machine Reading of Historical Events
Revisiting Unsupervised Relation Extraction
SciREX: A Challenge Dataset for Document-Level Information Extraction
Contrastive Self-Supervised Learning for Commonsense Reasoning RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers The Sensitivity of Language Models and Humans to Winograd Schema Perturbations Temporally-Informed Analysis of Named Entity Recognition Towards Open Domain Event Trigger Identification using Adversarial Domain Adaptation Cross-Modality Relevance for Reasoning on Language and Vision Hard-Coded Gaussian Attention for Neural Machine Translation The Paradigm Discovery Problem Supervised Grapheme-to-Phoneme Conversion of Orthographic Schwas in Hindi and Punjabi Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension BLEURT: Learning Robust Metrics for Text Generation Distilling Knowledge Learned in BERT for Text Generation ESPRIT: Explaining Solutions to Physical Reasoning Tasks Iterative Edit-Based Unsupervised Sentence Simplification Logical Natural Language Generation from Open-Domain Tables Neural CRF Model for Sentence Alignment in Text Simplification One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge Structural Information Preserving for Graph-to-Text Generation
Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding
From English to Code-Switching: Transfer Learning with Strong Morphological Clues Rationalizing Medical Relation Prediction from Corpus-level Statistics Sources of Transfer in Multilingual Named Entity Recognition Soft Gazetteers for Low-Resource Named Entity Recognition Empower Entity Set Expansion via Language Model Probing Feature Projection for Improved Text Classification History for Visual Dialog: Do we really need it? Mapping Natural Language Instructions to Mobile UI Action Sequences TVQA+: Spatio-Temporal Grounding for Video Question Answering Improving Chinese Word Segmentation with Wordhood Memory Networks Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge Phonetic and Visual Priors for Decipherment of Informal Romanization Active Learning for Coreference Resolution using Discrete Annotation Beyond Possession Existence: Duration and Co-Possession Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks Exploring Unexplored Generalization Challenges for Cross-Database Semantic Parsing Predicting the Focus of Negation: Model and Error Analysis Structured Tuning for Semantic Role Labeling A Generate-and-Rank Framework with Semantic Type Regularization for Biomedical Concept Normalization Hierarchical Entity Typing via Multi-level Learning to Rank TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition Balancing Training for Multilingual Neural Machine Translation A Multi-Perspective Architecture for Semantic Code Search DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking Multi-Label and Multilingual News Framing Analysis Predicting Performance for Natural Language Processing Tasks ScriptWriter: Narrative-Guided Script Generation Should All Cross-Lingual Embeddings Speak English? Smart To-Do: Automatic Generation of To-Do Items from Emails End-to-End Bias Mitigation by Modelling Biases in Corpora Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance NILE : Natural Language Inference with Faithful Natural Language Explanations QuASE: Question-Answer Driven Sentence Encoding Towards Robustifying NLI Models Against Lexical Dataset Biases Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches Revisiting Higher-Order Dependency Parsers Treebank Embedding Vectors for Out-of-domain Dependency Parsing
A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction