naacl 2021 论文列表
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6-11, 2021.
|
Inference Time Style Control for Summarization.
Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection.
MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization.
MM-AVS: A Full-Scale Dataset for Multi-modal Summarization.
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization.
AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization.
Sliding Selector Network with Dynamic Memory for Extractive Summarization of Long Documents.
Unsupervised Multi-hop Question Answering by Question Generation.
Designing a Minimal Retrieve-and-Read System for Open-Domain Question Answering.
DAGN: Discourse-Aware Graph Network for Logical Reasoning.
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering.
Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph.
Breadth First Reasoning Graph for Multi-hop Question Answering.
TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference.
Machine Translated Text Detection Through Text Similarity with Round-Trip Translation.
Context-aware Decoder for Neural Machine Translation using a Target-side Document-Level Language Model.
Rethinking Perturbations in Encoder-Decoders for Fast Training.
Training Data Augmentation for Code-Mixed Translation.
Non-Autoregressive Translation by Learning Target Categorical Codes.
Generative Imagination Elevates Machine Translation.
Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in Twitter.
SGG: Learning to Select, Guide, and Generate for Keyphrase Generation.
Multi-Grained Knowledge Distillation for Named Entity Recognition.
Jointly Extracting Explicit and Implicit Relational Triples with Reasoning Pattern Enhanced Binary Pointer Network.
Open Hierarchical Relation Extraction.
RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion.
Measuring the 'I don't know' Problem through the Lens of Gricean Quantity.
Hierarchical Transformer for Task Oriented Dialog Systems.
Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking.
Adversarial Self-Supervised Learning for Out-of-Domain Detection.
Augmenting Knowledge-grounded Conversations with Sequential Knowledge Transition.
Unsupervised Concept Representation Learning for Length-Varying Text Similarity.
NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction.
AMR Parsing with Action-Pointer Transformer.
Contextualized and Generalized Sentence Representations by Contrastive Self-Supervised Learning: A Case Study on Discourse Relation Analysis.
ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser.
Universal Semantic Tagging for English and Mandarin Chinese.
GPT Perdetry Test: Generating new meanings for new words.
User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical Normalization.
Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation.
Pre-training with Meta Learning for Chinese Word Segmentation.
Do RNN States Encode Abstract Phonological Alternations?
Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning.
Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model.
On Unifying Misinformation Detection.
Discrete Argument Representation Learning for Interactive Argument Pair Identification.
Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects.
Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction.
TITA: A Two-stage Interaction and Topic-Aware Text Matching Model.
Supporting Clustering with Contrastive Learning.
Self-training Improves Pre-training for Natural Language Understanding.
Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection.
Targeted Adversarial Training for Natural Language Understanding.
BBAEG: Towards BERT-based Biomedical Adversarial Example Generation for Text Classification.
Probing Contextual Language Models for Common Ground with Visual Representations.
Multitasking Inhibits Semantic Drift.
Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions.
OCID-Ref: A 3D Robotic Dataset With Embodied Language For Clutter Scene Grounding.
MIMOQA: Multimodal Input Multimodal Output Question Answering.
Multimodal End-to-End Sparse Model for Emotion Recognition.
Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation.
A Deep Metric Learning Approach to Account Linking.
Text Editing by Command.
SpanPredict: Extraction of Predictive Document Spans with Neural Attention.
AVA: an Automatic eValuation Approach for Question Answering Systems.
Nutri-bullets Hybrid: Consensual Multi-document Summarization.
Learning How to Ask: Querying LMs with Mixtures of Soft Prompts.
SCRIPT: Self-Critic PreTraining of Transformers.
ReadTwice: Reading Very Large Documents with Memories.
Revisiting Simple Neural Probabilistic Language Models.
On the Transformer Growth for Progressive BERT Training.
Limitations of Autoregressive Models and Their Alternatives.
On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies.
Too Much in Common: Shifting of Embeddings in Transformer Language Models and its Implications.
Evaluating the Values of Sources in Transfer Learning.
DirectProbe: Studying Representations without Classifiers.
Contextualized Perturbation for Textual Adversarial Attack.
Evaluating Saliency Methods for Neural Language Models.
Factual Probing Is [MASK]: Learning vs. Learning to Recall.
Attention Head Masking for Inference Time Content Selection in Abstractive Summarization.
An Empirical Study on Neural Keyphrase Generation.
Paragraph-level Simplification of Medical Texts.
ENTRUST: Argument Reframing with Language Models and Entailment.
Hurdles to Progress in Long-form Question Answering.
A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation.
Modeling Human Mental States with an Entity-based Narrative Graph.
Identifying inherent disagreement in natural language inference.
Profiling of Intertextuality in Latin Literature Using Word Embeddings.
Self Promotion in US Congressional Tweets.
Multitask Learning for Emotionally Analyzing Sexual Abuse Disclosures.
TuringAdvice: A Generative and Dynamic Evaluation of Language Use.
What Will it Take to Fix Benchmarking in Natural Language Understanding?
GSum: A General Framework for Guided Neural Abstractive Summarization.
Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics.
What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization.
Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization.
Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters.
Adversarial Learning for Zero-Shot Stance Detection on Social Media.
Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks.
Learning Paralinguistic Features from Audiobooks through Style Voice Conversion.
Knowledge Enhanced Masked Language Model for Stance Detection.
Seq2Emo: A Sequence to Multi-Label Emotion Classification Model.
Event Representation with Sequential, Semi-Supervised Discrete Variables.
Constructing Taxonomies from Pretrained Language Models.
Recent advances in neural metaphor processing: A linguistic, cognitive and social perspective.
ESC: Redesigning WSD with Extractive Sense Comprehension.
Scalar Adjective Identification and Multilingual Ranking.
Scalable and Interpretable Semantic Change Detection.
Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval.
Does Structure Matter? Encoding Documents for Machine Reading Comprehension.
Differentiable Open-Ended Commonsense Reasoning.
A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers.
SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning.
If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering.
Time-Stamped Language Model: Teaching Language Models to Understand The Flow of Events.
Adapting Coreference Resolution for Processing Violent Death Narratives.
Data and Model Distillation as a Solution for Domain-transferable Fact Verification.
On the Use of Context for Predicting Citation Worthiness of Sentences in Scholarly Articles.
Leveraging Deep Representations of Radiology Reports in Survival Analysis for Predicting Heart Failure Patient Mortality.
Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality.
Constrained Multi-Task Learning for Event Coreference Resolution.
Extracting a Knowledge Base of Mechanisms from COVID-19 Papers.
On Biasing Transformer Attention Towards Monotonicity.
Ab Antiquo: Neural Proto-language Reconstruction.
Linguistic Complexity Loss in Text-Based Therapy.
Word Complexity is in the Eye of the Beholder.
How (Non-)Optimal is the Lexicon?
Finding Concept-specific Biases in Form-Meaning Associations.
Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction.
Identifying Medical Self-Disclosure in Online Communities.
"I'm Not Mad": Commonsense Implications of Negation and Contradiction.
Swords: A Benchmark for Lexical Substitution with Improved Data Coverage and Quality.
MultiOpEd: A Corpus of Multi-Perspective News Editorials.
Plot-guided Adversarial Example Construction for Evaluating Open-domain Story Generation.
SOCCER: An Information-Sparse Discourse State Tracking Collection in the Sports Commentary Domain.
Progressive Generation of Long Text with Pretrained Language Models.
Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge.
NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints.
Focused Attention Improves Document-Grounded Generation.
On Learning Text Style Transfer with Direct Rewards.
MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding.
TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class Names.
Self-Alignment Pretraining for Biomedical Entity Representations.
Inductive Topic Variational Graph Auto-Encoder for Text Classification.
Multi-source Neural Topic Modeling in Multi-view Embedding Spaces.
CoRT: Complementary Rankings from Transformers.
Redefining Absent Keyphrases and their Effect on Retrieval Effectiveness.
Stay Together: A System for Single and Split-antecedent Anaphora Resolution.
Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models.
Probing for Bridging Inference in Transformer Language Models.
Predicting Discourse Trees from Transformer-based Neural Summarizers.
Translational NLP: A New Paradigm and General Principles for Natural Language Processing Research.
Dynabench: Rethinking Benchmarking in NLP.
Causal Effects of Linguistic Properties.
How low is too low? A monolingual take on lemmatisation in Indian languages.
Grey-box Adversarial Attack And Defence For Sentiment Classification.
A recipe for annotating grounded clarifications.
Self-Supervised Contrastive Learning for Efficient User Satisfaction Prediction in Conversational Agents.
Modeling Diagnostic Label Correlation for Automatic ICD Coding.
Restoring and Mining the Records of the Joseon Dynasty via Neural Language Modeling and Machine Translation.
Quantitative Day Trading from Natural Language using Reinforcement Learning.
Distantly Supervised Transformers For E-Commerce Product QA.
ER-AE: Differentially Private Text Generation for Authorship Anonymization.
Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation.
Smart-Start Decoding for Neural Machine Translation.
Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios.
Continual Learning for Neural Machine Translation.
Multi-Hop Transformer for Document-Level Machine Translation.
Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation.
Almost Free Semantic Draft for Neural Machine Translation.
Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks.
Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation.
Learning to Learn to be Right for the Right Reasons.
tWT-WT: A Dataset to Assert the Role of Target Entities for Detecting Stance of Tweets.
UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost.
Discourse Probing of Pretrained Language Models.
Topic Model or Topic Twaddle? Re-evaluating Semantic Interpretability Measures.
On the Impact of Random Seeds on the Fairness of Clinical Classifiers.
Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels.
Case Study: Deontological Ethics in NLP.
On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning.
Beyond Fair Pay: Ethical Implications of NLP Crowdsourcing.
An Empirical Investigation of Bias in the Multimodal Analysis of Financial Earnings Calls.
Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial Attack.
QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval.
Universal Adversarial Attacks with Natural Triggers for Text Classification.
Refining Targeted Syntactic Evaluation of Language Models.
CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images.
Adaptable and Interpretable Neural MemoryOver Symbolic Knowledge.
multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning.
Wikipedia Entities as Rendezvous across Languages: Grounding Multilingual Language Models by Predicting Wikipedia Hyperlinks.
Cross-lingual Cross-modal Pretraining for Multimodal Retrieval.
Explicit Alignment Objectives for Multilingual Bidirectional Encoders.
X-METRA-ADA: Cross-lingual Meta-Transfer learning Adaptation to Natural Language Understanding and Question Answering.
Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots.
Context-Interactive Pre-Training for Document Machine Translation.
InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training.
Choose Your Own Adventure: Paired Suggestions in Collaborative Writing for Evaluating Story Generation Models.
Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training.
Controllable Text Simplification with Explicit Paraphrasing.
FUDGE: Controlled Text Generation With Future Discriminators.
Multi-Style Transfer with Discriminative Feedback on Disjoint Corpus.
A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution.
Graph Convolutional Networks for Event Causality Identification with Rich Document-level Structures.
ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning.
Better Feature Integration for Named Entity Recognition.
TABBIE: Pretrained Representations of Tabular Data.
Noisy-Labeled NER with Confidence Estimation.
Integrating Lexical Information into Entity Neighbourhood Representations for Relation Prediction.
Clipping Loops for Sample-Efficient Dialogue Policy Optimisation.
Knowledge-Driven Slot Constraints for Goal-Oriented Dialogue Systems.
CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues.
ConVEx: Data-Efficient and Few-Shot Slot Labeling.
Supervised Neural Clustering via Latent Structured Output Learning: Application to Question Intents.
Ensemble of MRR and NDCG models for Visual Dialog.
Knowledge Guided Metric Learning for Few-Shot Text Classification.
HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization.
FlowPrior: Learning Expressive Priors for Latent Variable Sentence Models.
Noise Stability Regularization for Improving BERT Fine-tuning.
Grouping Words with Semantic Diversity.
Olá, Bonjour, Salve! XFORMAL: A Benchmark for Multilingual Formality Style Transfer.
News Headline Grouping as a Challenging NLU Task.
CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems.
Quality Estimation for Image Captions Based on Large-scale Human Evaluations.
SentSim: Crosslingual Semantic Evaluation of Machine Translation.
Negative language transfer in learner English: A new dataset.
Revisiting Document Representations for Large-Scale Zero-Shot Learning.
Semi-Supervised Policy Initialization for Playing Games with Language Hints.
SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency.
Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents.
You Sound Like Someone Who Watches Drama Movies: Towards Predicting Movie Preferences from Conversational Interactions.
Faithfully Explainable Recommendation via Neural Logic Reasoning.
Exploring the Relationship Between Algorithm Performance, Vocabulary, and Run-Time in Text Classification.
Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modeling.
X-Class: Text Classification with Extremely Weak Supervision.
COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List.
Controlling Dialogue Generation with Semantic Exemplars.
Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems.
Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management.
Example-Driven Intent Prediction with Observers.
Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog.
Bot-Adversarial Dialogue for Safe Conversational Agents.
Learning Syntax from Naturally-Occurring Bracketings.
Outside Computation with Superior Functions.
Supertagging-based Parsing with Linear Context-free Rewriting Systems.
Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer Ensemble.
Emotion-Infused Models for Explainable Psychological Stress Detection.
Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification.
A Disentangled Adversarial Neural Topic Model for Separating Opinions from Plots in User Reviews.
Multi-task Learning of Negation and Speculation for Targeted Sentiment Classification.
Domain Adaptation for Arabic Cross-Domain and Cross-Dialect Sentiment Analysis from Contextualized Word Embedding.
Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention.
Incorporating External Knowledge to Enhance Tabular Reasoning.
Game-theoretic Vocabulary Selection via the Shapley Value and Banzhaf Index.
FLIN: A Flexible Natural Language Interface for Web Navigation.
Edge: Enriching Knowledge Graph Embeddings with External Text.
Learning to Synthesize Data for Semantic Parsing.
Learning from Executions for Semantic Parsing.
Continual Learning for Text Classification with Information Disentanglement Based Regularization.
Learning to Decompose and Organize Complex Tasks.
MUSER: MUltimodal Stress detection using Emotion Recognition as an Auxiliary Task.
Semantic Frame Forecast.
Cross-Lingual Word Embedding Refinement by $\ell_1$ Norm Optimisation.
On the Embeddings of Variables in Recurrent Neural Networks for Source Code.
Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding.
Unified Pre-training for Program Understanding and Generation.
Smoothing and Shrinking the Sparse Seq2Seq Search Space.
Can Latent Alignments Improve Autoregressive Machine Translation?
How many data points is a prompt worth?
Diversity-Aware Batch Active Learning for Dependency Parsing.
Variance-reduced First-order Meta-learning for Natural Language Processing Tasks.
Clustering-based Inference for Biomedical Entity Linking.
Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning.
UDALM: Unsupervised Domain Adaptation through Language Modeling.
Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector Embeddings.
A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios.
KILT: a Benchmark for Knowledge Intensive Language Tasks.
Challenging distributional models with a conceptual network of philosophical terms.
WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia.
From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding.
Video Question Answering with Phrases via Semantic Roles.
Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models.
Improving Generation and Evaluation of Visual Stories via Semantic Consistency.
DeCEMBERT: Learning from Noisy Instructional Videos via Dense Captions and Entropy Minimization.
EaSe: A Diagnostic Tool for VQA based on Answer Diversity.
HONEST: Measuring Hurtful Sentence Completion in Language Models.
Detoxifying Language Models Risks Marginalizing Minority Voices.
Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained Transformers.
Rethinking Network Pruning - under the Pre-train and Fine-tune Paradigm.
Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis.
Static Embeddings as Efficient Knowledge Bases?
It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners.
Learning to Recognize Dialect Features.
Lifelong Learning of Hate Speech Classification on Social Media.
Introducing CAD: the Contextual Abuse Dataset.
What About the Precedent: An Information-Theoretic Analysis of Common Law.
Modeling the Severity of Complaints in Social Media.
Modeling Framing in Immigration Discourse on Social Media.
The structure of online social networks modulates the rate of lexical change.
WikiTalkEdit: A Dataset for modeling Editors' behaviors on Wikipedia.
Suicide Ideation Detection via Social and Temporal User Representations using Hyperbolic Learning.
Automatic Classification of Neutralization Techniques in the Narrative of Climate Change Scepticism.
Framing Unpacked: A Semi-Supervised Interpretable Multi-View Model of Media Frames.
COVID-19 Named Entity Recognition for Vietnamese.
Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge.
StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer.
KPQA: A Metric for Generative Question Answering Using Keyphrase Weights.
WRIME: A New Dataset for Emotional Intensity Estimation with Subjective and Objective Annotations.
Are NLP Models really able to Solve Simple Math Word Problems?
ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction.
DA-Transformer: Distance-aware Transformer.
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models.
Heterogeneous Graph Neural Networks for Concept Prerequisite Relation Learning in Educational Data.
Masked Conditional Random Fields for Sequence Labeling.
A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models.
Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!
Generating An Optimal Interview Question Plan Using A Knowledge Graph And Integer Linear Programming.
Active² Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation.
Towards Few-shot Fact-Checking via Perplexity.
Personalized Response Generation via Generative Split Memory Network.
Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph Network.
Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis.
Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment.
Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering.
SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding.
Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks.
Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation.
End-to-end ASR to jointly predict transcriptions and linguistic annotations.
Target-Aware Data Augmentation for Stance Detection.
Domain Divergences: A Survey and Empirical Analysis.
Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa.
Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words Extraction.
A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents.
Why Do Document-Level Polarity Classifiers Fail?
Non-Parametric Few-Shot Learning for Word Sense Disambiguation.
MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories.
Field Embedding: A Unified Grain-Based Framework for Word Representation.
UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System Metathesaurus.
Modeling Event Plausibility with Consistent Conceptual Abstraction.
Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models.
ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding.
Mask Attention Networks: Rethinking and Strengthen Transformer.
Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study.
Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation.
Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle.
Bridging Resolution: Making Sense of the State of the Art.
Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance.
Did they answer? Subjective acts and intents in conversational discourse.
RST Parsing from Scratch.
Improving Neural RST Parsing Model with Silver Agreement Subtrees.
Context Tracking Network: Graph-based Context Modeling for Implicit Discourse Relation Recognition.
Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention Network.
Adding Chit-Chat to Enhance Task-Oriented Dialogues.
Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention.
Fine-grained Post-training for Improving Retrieval-based Dialogue Systems.
How Robust are Fact Checking Systems on Colloquial Claims?
Generating Negative Samples by Manipulating Golden Responses for Unsupervised Learning of a Response Evaluation Model.
Video-aided Unsupervised Grammar Induction.
GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context Input.
PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols.
Neural Sequence Segmentation as Determining the Leftmost Segments.
Larger-Context Tagging: When and Why Does It Work?
Annotating and Modeling Fine-grained Factuality in Summarization.
RefSum: Refactoring Neural Summarization.
Efficient Attentions for Long Document Summarization.
D2S: Document-to-Slide Generation Via Query-Based Text Summarization.
A New Approach to Overgenerating and Scoring Abstractive Summaries.
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs.
Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models.
Temporal Reasoning on Implicit Events from Distant Supervision.
Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System.
Structure-Grounded Pretraining for Text-to-SQL.
Looking Beyond Sentence-Level Natural Language Inference for Question Answering and Text Summarization.
DuoRAT: Towards Simpler Text-to-SQL Models.
Understanding by Understanding Not: Modeling Negation in Language Models.
On the Transferability of Minimal Prediction Preserving Inputs in Question Answering.
RECONSIDER: Improved Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answering.
Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models.
Robust Question Answering Through Sub-part Alignment.
Explainable Multi-hop Verbal Reasoning Through Internal Monologue.
Capturing Row and Column Semantics in Transformer Based Question Answering over Tables.
Self-Supervised Test-Time Learning for Reading Comprehension.
Towards Modeling the Style of Translators in Neural Machine Translation.
Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution.
The Curious Case of Hallucinations in Neural Machine Translation.
Assessing Reference-Free Peer Evaluation for Machine Translation.
Macro-Average: Rare Types Are Important Too.
Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages.
DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference.
Certified Robustness to Word Substitution Attack with Differential Privacy.
Understanding Hard Negatives in Noise Contrastive Estimation.
Posterior Differential Regularization with f-divergence for Improving Model Robustness.
Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach.
Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning.
Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information.
Modular Networks for Compositional Instruction Following.
Grounding Open-Domain Instructions to Automate Web Support Tasks.
MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences.
Measuring Social Biases in Grounded Vision and Language Embeddings.
LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval.
Generalization in Instruction Following Systems.
An Empirical Comparison of Instance Attribution Methods for NLP.
Low-Complexity Probing via Finding Subnetworks.
Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?
On Attention Redundancy: A Comprehensive Study.
Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU models.
Template Filling with Generative Transformers.
Document-Level Event Argument Extraction by Conditional Generation.
Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning.
Neural Language Modeling for Contextualized Temporal Graph Generation.
Self-Training with Weak Supervision.
Linking Entities to Unseen Knowledge Bases with Arbitrary Schemas.
How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds.
Spoken Language Understanding for Task-oriented Dialogue Systems with Augmented Memory Networks.
A Comparative Study on Schema-Guided Dialogue State Tracking.
Human-like informative conversations: Better acknowledgements using conditional mutual information.
"Nice Try, Kiddo": Investigating Ad Hominems in Dialogue Responses.
Few-shot Intent Classification and Slot Filling with Retrieved Examples.
Enhancing Factual Consistency of Abstractive Summarization.
Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation.
Noisy Self-Knowledge Distillation for Text Summarization.
Identifying Helpful Sentences in Product Reviews.
Extending Multi-Document Summarization Evaluation to the Interactive Setting.
Representing Numbers in NLP: a Survey and a Vision.
Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence.
Preregistering NLP research.
On learning and representing social meaning in NLP: a sociolinguistic perspective.
The Importance of Modeling Social Factors of Language: Theory and Practice.
Implicitly Abusive Language - What does it actually look like and why are we not getting there?
SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval.
XOR QA: Cross-lingual Open-Retrieval Question Answering.
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering.
Open-Domain Question Answering Goes Conversational via Question Rewriting.
Open Domain Question Answering over Tables via Dense Retrieval.
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning.
mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer.
Multi-view Subword Regularization.
Multi-Adversarial Learning for Cross-Lingual Word Embeddings.
When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models.
DART: Open-Domain Structured Data Record to Text Generation.
APo-VAE: Text Generation in Hyperbolic Space.
Text Generation from Discourse Representation Structures.
Aspect-Controlled Neural Argument Generation.
Meta-Learning for Domain Generalization in Semantic Parsing.
Fool Me Twice: Entailment from Wikipedia Gamification.
Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources.
SGL: Speaking the Graph Languages of Semantic Parsing via Multilingual Translation.
SmBoP: Semi-autoregressive Bottom-up Semantic Parsing.
Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks.
Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition.
A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code.
DATE: Detecting Anomalies in Text via Self-Supervision of Transformers.
EnSidNet: Enhanced Hybrid Siamese-Deep Network for grouping clinical trials into drug-development pathways.
Answering Product-Questions by Utilizing Questions from Other Contextually Similar Products.
Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases.
A Million Tweets Are Worth a Few Points: Tuning Transformers for Customer Service Tasks.
Multilingual BERT Post-Pretraining Alignment.
Cultural and Geographical Influences on Image Translatability of Words across Languages.
Counterfactual Data Augmentation for Neural Machine Translation.
Neural Machine Translation without Embeddings.
Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation.
Data Filtering using Cross-Lingual Word Embeddings.
Backtranslation Feedback Improves User Confidence in MT, Not Quality.
Concealed Data Poisoning Attacks on NLP Models.
A Non-Linear Structural Probe.
Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing.
Multilingual Language Models Predict Human Reading Behavior.
Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA.
Mediators in Determining what Processing BERT Performs First.
Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers.
Event Time Extraction and Propagation via Graph Attention Networks.
A Frustratingly Easy Approach for Entity and Relation Extraction.
Abstract Meaning Representation Guided Graph Encoding and Decoding for Joint Information Extraction.
Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks.
Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors.
Knowledge Router: Learning Disentangled Representations for Knowledge Graphs.
