emnlp 2021 论文列表
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021.
|
Detecting Contact-Induced Semantic Shifts: What Can Embedding-Based Methods Do in Practice?
Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration.
Semi-Supervised Exaggeration Detection of Health Science Press Releases.
GeneSis: A Generative Approach to Substitutes in Context.
Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization.
VeeAlign: Multifaceted Context Representation Using Dual Attention for Ontology Alignment.
Is Everything in Order? A Simple Way to Order Sentences.
Multivalent Entailment Graphs for Question Answering.
Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning.
Softmax Tree: An Accurate, Fast Classifier When the Number of Classes Is Large.
MTAdam: Automatic Balancing of Multiple Training Loss Terms.
Self-training with Few-shot Rationalization.
Types of Out-of-Distribution Texts and How to Detect Them.
Pushing on Text Readability Assessment: A Transformer Meets Handcrafted Linguistic Features.
IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization.
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression.
How to Train BERT with an Academic Budget.
Finetuning Pretrained Transformers into RNNs.
Block Pruning For Faster Transformers.
PermuteFormer: Efficient Relative Position Encoding for Long Sequences.
What to Pre-Train on? Efficient Intermediate Task Selection.
A New Representation for Span-based CCG Parsing.
Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering.
Efficient Sampling of Dependency Structure.
A Root of a Problem: Optimizing Single-Root Dependency Parsing.
Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement.
IndoNLI: A Natural Language Inference Dataset for Indonesian.
Robustness Evaluation of Entity Disambiguation Using Prior Probes: the Case of Entity Overshadowing.
Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema.
Visually Grounded Reasoning across Languages and Cultures.
Automatic Text Evaluation through the Lens of Wasserstein Barycenters.
Separating Retention from Extraction in the Evaluation of End-to-end Relation Extraction.
Utilizing Relative Event Time to Enhance Event-Event Temporal Relation Extraction.
XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment.
Few-Shot Named Entity Recognition: An Empirical Baseline Study.
HittER: Hierarchical Transformers for Knowledge Graph Embeddings.
Open Knowledge Graphs Canonicalization using Variational Autoencoders.
Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training.
Studying word order through iterative shuffling.
FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging.
Rationales for Sequential Predictions.
Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords.
Discretized Integrated Gradients for Explaining Language Models.
Measuring Association Between Labels and Free-Text Rationales.
Contrastive Conditioning for Assessing Disambiguation in MT: A Case Study of Distilled Bias.
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation.
Neural Machine Translation Quality and Post-Editing Performance.
UNKs Everywhere: Adapting Multilingual Language Models to New Scripts.
Investigating the Helpfulness of Word-Level Quality Estimation for Post-Editing Machine Translation Output.
AUTOSUMM: Automatic Model Creation for Text Summarization.
MassiveSumm: a very large-scale, very multilingual, news summarisation dataset.
Chinese Opinion Role Labeling with Corpus Translation: A Pivot Study.
On Classifying whether Two Texts are on the Same Side of an Argument.
The Effect of Efficient Messaging and Input Variability on Neural-Agent Iterated Language Learning.
An Information-Theoretic Characterization of Morphological Fusion.
A Simple Geometric Method for Cross-Lingual Linguistic Transformations with Pre-trained Autoencoders.
PAUSE: Positive and Annealed Unlabeled Sentence Embedding.
"Was it "stated" or was it "claimed"?: How linguistic bias affects generative language models.
"So You Think You're Funny?": Rating the Humour Quotient in Standup Comedy.
SWEAT: Scoring Polarization of Topics across Different Corpora.
Learning Bill Similarity with Annotated and Augmented Corpora of Bills.
Rumor Detection on Twitter with Claim-Guided Hierarchical Graph Attention Networks.
Assessing the Reliability of Word Embedding Gender Bias Measures.
Measuring Sentence-Level and Aspect-Level (Un)certainty in Science Communications.
Identifying Morality Frames in Political Tweets using Relational Learning.
Using Sociolinguistic Variables to Reveal Changing Attitudes Towards Sexuality and Gender.
Guilt by Association: Emotion Intensities in Lexical Representations.
Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings.
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models.
QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions.
Integrating Deep Event-Level and Script-Level Information for Script Event Prediction.
HypMix: Hyperbolic Interpolative Data Augmentation.
Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers.
COVR: A Test-Bed for Visually Grounded Compositional Generalization with Real Images.
On Pursuit of Designing Multi-modal Transformer for Video Grounding.
Inflate and Shrink: Enriching and Reducing Interactions for Fast Text-Image Retrieval.
Jointly Learning to Repair Code and Generate Commit Message.
Wasserstein Selective Transfer Learning for Cross-domain Text Mining.
UniKER: A Unified Framework for Combining Embedding and Definite Horn Rule Reasoning for Knowledge Graph Inference.
Meta Distant Transfer Learning for Pre-trained Language Models.
A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis.
Exploring Methods for Generating Feedback Comments for Writing Learning.
A Relation-Oriented Clustering Method for Open Relation Extraction.
Maximal Clique Based Non-Autoregressive Open Information Extraction.
Uncovering Main Causalities for Long-tailed Information Extraction.
Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion.
Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction.
Set Generation Networks for End-to-End Knowledge Base Population.
Numerical reasoning in machine reading comprehension tasks: are we there yet?
Evaluation Paradigms in Question Answering.
What's in a Name? Answer Equivalence For Open-Domain Question Answering.
Distantly-Supervised Dense Retrieval Enables Open-Domain Question Answering without Evidence Annotation.
Case-based Reasoning for Natural Language Queries over Knowledge Bases.
Contrastive Domain Adaptation for Question Answering using Limited Text Corpora.
Value-aware Approximate Attention.
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks.
KnowMAN: Weakly Supervised Multinomial Adversarial Networks.
Knowledge Graph Representation Learning using Ordinary Differential Equations.
Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning.
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP.
Neuralizing Regular Expressions for Slot Filling.
Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling.
Revisiting Tri-training of Dependency Parsers.
Enriching and Controlling Global Semantics for Text Summarization.
Learning Opinion Summarizers by Selecting Informative Reviews.
Models and Datasets for Cross-Lingual Summarisation.
ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization.
BARThez: a Skilled Pretrained French Sequence-to-Sequence Model.
Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems.
Caption Enriched Samples for Improving Hateful Memes Detection.
A Unified Speaker Adaptation Approach for ASR.
Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy.
R\^3Net: Relation-embedded Representation Reconstruction Network for Change Captioning.
Language Models are Few-Shot Butlers.
Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding.
Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos.
PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction.
Exploring Non-Autoregressive Text Style Transfer.
Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style Transfer.
Towards Label-Agnostic Emotion Embeddings.
Cross-lingual Aspect-based Sentiment Analysis with Aspect Term Code-Switching.
Aspect Sentiment Quad Prediction as Paraphrase Generation.
Does Social Pressure Drive Persuasion in Online Fora?
BERT4GCN: Using BERT Intermediate Layers to Augment GCN for Aspect-based Sentiment Classification.
Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis.
An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction.
YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews.
Unimodal and Crossmodal Refinement Network for Multimodal Sequence Fusion.
Bridging Perception, Memory, and Inference through Semantic Relations.
Revisiting Self-training for Few-shot Learning of Language Model.
NB-MLM: Efficient Domain Adaptation of Masked Language Models for Sentiment Analysis.
Cross-lingual Sentence Embedding using Multi-Task Learning.
Integrating Personalized PageRank into Neural Word Sense Disambiguation.
A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing.
Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning.
Distilling Relation Embeddings from Pretrained Language Models.
Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification.
Cross-Domain Label-Adaptive Stance Detection.
Time-aware Graph Neural Network for Entity Alignment between Temporal Knowledge Graphs.
SPARQLing Database Queries from Intermediate Question Decompositions.
Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing.
Enhancing the Context Representation in Similarity-based Word Sense Disambiguation.
Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset.
NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender Neutral Alternatives.
What happens if you treat ordinal ratings as interval data? Human evaluations in NLP are even more under-powered than you think.
Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization.
Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors.
Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability.
IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation.
MLEC-QA: A Chinese Multi-Choice Biomedical Question Answering Dataset.
BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief.
Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation.
Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs.
Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection.
English Machine Reading Comprehension Datasets: A Survey.
Finnish Dialect Identification: The Effect of Audio and Text.
ClauseRec: A Clause Recommendation Framework for AI-aided Contract Authoring.
Self-Supervised Detection of Contextual Synonyms in a Multi-Class Setting: Phenotype Annotation Use Case.
To Share or not to Share: Predicting Sets of Sources for Model Transfer Learning.
Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models.
Multi-Class Grammatical Error Detection for Correction: A Tale of Two Systems.
Detect and Classify - Joint Span Detection and Classification for Health Outcomes.
CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation.
Preventing Author Profiling through Zero-Shot Multilingual Back-Translation.
STaCK: Sentence Ordering with Temporal Commonsense Knowledge.
BERT-Beta: A Proactive Probabilistic Approach to Text Moderation.
Parallel Refinements for Lexically Constrained Text Generation with BART.
Unsupervised Multi-View Post-OCR Error Correction With Language Models.
Meta-LMTC: Meta-Learning for Large-Scale Multi-Label Text Classification.
Cross-Policy Compliance Detection via Question Answering.
Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search Degradation.
Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification.
Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan Languages.
Efficient Inference for Multilingual Neural Machine Translation.
Vision Matters When It Should: Sanity Checking Multimodal Machine Translation Models.
Discrete and Soft Prompting for Multilingual Models.
One Source, Two Targets: Challenges and Rewards of Dual Decoding.
Wino-X: Multilingual Winograd Schemas for Commonsense Reasoning and Coreference Resolution.
Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach.
Effective Fine-Tuning Methods for Cross-lingual Adaptation.
Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT.
Improving the Quality Trade-Off for Neural Machine Translation Multi-Domain Adaptation.
Graph Algorithms for Multiparallel Word Alignment.
An Empirical Investigation of Word Alignment Supervision for Zero-Shot Multilingual Neural Machine Translation.
Document Graph for Neural Machine Translation.
Machine Translation Decoding beyond Beam Search.
A Strong Baseline for Query Efficient Attacks in a Black Box Setting.
FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations.
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models.
Learning Neural Ordinary Equations for Forecasting Future Links on Temporal Knowledge Graphs.
BiQUE: Biquaternionic Embeddings of Knowledge Graphs.
Code-switched inspired losses for spoken dialog representations.
TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting.
Synthetic Textual Features for the Large-Scale Detection of Basic-level Categories in English and Mandarin.
On Homophony and Rényi Entropy.
Is Information Density Uniform in Task-Oriented Dialogues?
Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification.
Sequence Length is a Domain: Length-based Overfitting in Transformer Models.
Locke's Holiday: Belief Bias in Machine Reading.
Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods.
Don't Search for a Search Method - Simple Heuristics Suffice for Adversarial Text Attacks.
What's in Your Head? Emergent Behaviour in Multi-Task Transformer Models.
Enjoy the Salience: Towards Better Transformer-based Faithful Explanations with Word Salience.
Bayesian Topic Regression for Causal Inference.
Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution.
Deep Attention Diffusion Graph Neural Networks for Text Classification.
Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement.
Matching-oriented Embedding Quantization For Ad-hoc Retrieval.
Time-dependent Entity Embedding is not All You Need: A Re-evaluation of Temporal Knowledge Graph Completion Models under a Unified Framework.
Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction.
Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention.
Extracting Event Temporal Relations via Hyperbolic Geometry.
TDEER: An Efficient Translating Decoding Schema for Joint Extraction of Entities and Relations.
Low-Rank Subspaces for Unsupervised Entity Linking.
Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation.
Paraphrasing Compound Nominalizations.
A Bag of Tricks for Dialogue Summarization.
Document-Level Text Simplification: Dataset, Criteria and Baseline.
Text Detoxification using Large Pre-trained Neural Models.
CAPE: Context-Aware Private Embeddings for Private Language Learning.
Understanding and Overcoming the Challenges of Efficient Transformer Quantization.
AdapterDrop: On the Efficiency of Adapters in Transformers.
A Semantic Filter Based on Relations for Knowledge Graph Completion.
Dynamic Forecasting of Conversation Derailment.
Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance.
Zero-Shot Dialogue State Tracking via Cross-Task Transfer.
A Collaborative Multi-agent Reinforcement Learning Framework for Dialog Action Decomposition.
Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking.
$Q^2$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering.
Proxy Indicators for the Quality of Open-domain Dialogues.
Learning Neural Templates for Recommender Dialogue System.
#HowYouTagTweets: Learning User Hashtagging Preferences via Personalized Topic Attention.
Come hither or go away? Recognising pre-electoral coalition signals in the news.
Point-of-Interest Type Prediction using Text and Images.
Classifying Dyads for Militarized Conflict Analysis.
Language-agnostic Representation from Multilingual Sentence Encoders for Cross-lingual Similarity Estimation.
LM-Critic: Language Models for Unsupervised Grammatical Error Correction.
Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories.
ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning.
Constrained Language Models Yield Few-Shot Semantic Parsers.
Controllable Semantic Parsing via Retrieval Augmentation.
A Secure and Efficient Federated Learning Framework for NLP.
Word-Level Coreference Resolution.
Highly Parallel Autoregressive Entity Linking with Discriminative Correction.
Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation.
When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute.
Learning with Different Amounts of Annotation: From Zero to Many Labels.
MATE: Multi-view Attention for Table Transformer Efficiency.
Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation.
RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms.
ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations.
On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert Ratings.
CLIPScore: A Reference-free Evaluation Metric for Image Captioning.
MS\^2: Multi-Document Summarization of Medical Studies.
Effective Sequence-to-Sequence Dialogue State Tracking.
Investigating Robustness of Dialog Models to Popular Figurative Language Constructs.
Multilingual and Cross-Lingual Intent Detection from Spoken Data.
Continual Learning in Task-Oriented Dialogue Systems.
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach.
Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules.
ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Detection in Conversational AI.
SituatedQA: Incorporating Extra-Linguistic Contexts into QA.
Explaining Answers with Entailment Trees.
Learning with Instance Bundles for Reading Comprehension.
Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering.
How much coffee was consumed during EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI.
Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy.
Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training.
Learning Kernel-Smoothed Machine Translation with Retrieved Examples.
Improving Multilingual Translation by Representation and Gradient Regularization.
Don't Go Far Off: An Empirical Study on Neural Poetry Translation.
Robust Open-Vocabulary Translation from Visual Text Representations.
Perturbation CheckLists for Evaluating NLG Evaluation Metrics.
ValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries.
On the Influence of Masking Policies in Intermediate Pre-training.
CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP.
AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples.
Evaluating the Morphosyntactic Well-formedness of Generated Texts.
Does It Capture STEL? A Modular, Similarity-based Linguistic Style Evaluation Framework.
I Wish I Would Have Loved This One, But I Didn't - A Multilingual Dataset for Counterfactual Detection in Product Review.
DWUG: A large Resource of Diachronic Word Usage Graphs in Four Languages.
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval.
Entity-Based Knowledge Conflicts in Question Answering.
Surface Form Competition: Why the Highest Probability Answer Isn't Always Right.
Have You Seen That Number? Investigating Extrapolation in Question Answering Models.
Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering.
Generative Context Pair Selection for Multi-hop Question Answering.
Joint Passage Ranking for Diverse Multi-Answer Retrieval.
MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer.
Students Who Study Together Learn Better: On the Importance of Collective Knowledge Distillation for Domain Transfer in Fact Verification.
Numeracy enhances the Literacy of Language Models.
Continuous Entailment Patterns for Lexical Inference in Context.
Generating Datasets with Pretrained Language Models.
Aligning Actions Across Recipe Graphs.
When is Wall a Pared and when a Muro?: Extracting Rules Governing Lexical Selection.
SimCSE: Simple Contrastive Learning of Sentence Embeddings.
Implicit Sentiment Analysis with Event-centered Text Representation.
CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks.
Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks.
SYSML: StYlometry with Structure and Multitask Learning: Implications for Darknet Forum Migrant Analysis.
Tribrid: Stance Classification with Neural Inconsistency Detection.
Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer.
NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media.
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding.
Integrating Visuospatial, Linguistic, and Commonsense Structure into Story Visualization.
Visual News: Benchmark and Challenges in News Image Captioning.
Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech.
Interactive Machine Comprehension with Dynamic Knowledge Graphs.
Levenshtein Training for Word-level Quality Estimation.
Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation.
It Is Not As Good As You Think! Evaluating Simultaneous Machine Translation on Interpretation Data.
A Generative Framework for Simultaneous Machine Translation.
Controlling Machine Translation for Multiple Attributes with Additive Interventions.
BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation.
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters.
CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization.
Finding a Balanced Degree of Automation for Summary Evaluation.
Simple Conversational Data Augmentation for Semi-supervised Abstractive Dialogue Summarization.
QuestEval: Summarization Asks for Fact-based Evaluation.
Aspect-Controllable Opinion Summarization.
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach.
Towards Zero-Shot Knowledge Distillation for Natural Language Processing.
SPECTRA: Sparse Structured Text Rationalization.
Knowledge Base Completion Meets Transfer Learning.
Sparse Attention with Linear Units.
Editing Factual Knowledge in Language Models.
Cross-Register Projection for Headline Part of Speech Tagging.
StreamHover: Livestream Transcript Summarization and Annotation.
Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport.
NDH-Full: Learning and Evaluating Navigational Agents on Full-Length Dialogue.
Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering.
Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring Expressions.
Hitting your MARQ: Multimodal ARgument Quality Assessment in Long Debate Video.
Sequential Randomized Smoothing for Adversarially Robust Speech Recognition.
Improving Pre-trained Vision-and-Language Embeddings for Phrase Grounding.
Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering.
Improving Stance Detection with Multi-Dataset Learning and Knowledge Distillation.
Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica.
Open Aspect Target Sentiment Classification with Natural Language Prompts.
Think about it! Improving defeasible reasoning by first modeling the question scenario.
Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing.
Flexible Generation of Natural Language Deductions.
Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks.
Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models.
On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling.
Universal Sentence Representation Learning with Conditional Masked Language Model.
Data Collection vs. Knowledge Graph Completion: What is Needed to Improve Coverage?
BiSECT: Learning to Split and Rephrase Sentences with Bitexts.
GupShup: Summarizing Open-Domain Code-Switched Conversations.
MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents.
Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval Marginalization.
Simple Entity-Centric Questions Challenge Dense Retrievers.
Single-dataset Experts for Multi-dataset Question Answering.
ReasonBERT: Pre-trained to Reason with Distant Supervision.
Perhaps PTLMs Should Go to School - A Task to Assess Open Book and Closed Book QA.
Multi-stage Training with Improved Negative Contrast for Neural Passage Retrieval.
FewshotQA: A simple framework for few-shot learning of question answering tasks using pre-trained text-to-text models.
Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading Comprehension.
A Scalable Framework for Learning From Implicit User Feedback to Improve Natural Language Understanding in Large-Scale Conversational AI Systems.
Evaluating Scholarly Impact: Towards Content-Aware Bibliometrics.
A Semantic Feature-Wise Transformation Relation Network for Automatic Short Answer Grading.
Detecting Health Advice in Medical Research Literature.
Navigating the Kaleidoscope of COVID-19 Misinformation Using Deep Learning.
Math Word Problem Generation with Mathematical Consistency and Problem Context Constraints.
IGA: An Intent-Guided Authoring Assistant.
Contrastive Code Representation Learning.
Effective Convolutional Attention Network for Multi-label Clinical Document Classification.
Learning to Selectively Learn for Weakly-supervised Paraphrase Generation.
Good-Enough Example Extrapolation.
Data and Parameter Scaling Laws for Neural Machine Translation.
Rule-based Morphological Inflection Improves Neural Terminology Translation.
Analyzing the Surprising Variability in Word Embedding Stability Across Languages.
A Large-Scale Study of Machine Translation in Turkic Languages.
Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications.
Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings.
Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic Parsing.
A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space.
A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual Representations.
Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP.
Muppet: Massive Multi-task Representations with Pre-Finetuning.
Pairwise Supervised Contrastive Learning of Sentence Representations.
Paired Examples as Indirect Supervision in Latent Decision Models.
Do Transformer Modifications Transfer Across Implementations and Applications?
Gradient-based Adversarial Attacks against Text Transformers.
TADPOLE: Task ADapted Pre-Training via AnOmaLy DEtection.
STraTA: Self-Training with Task Augmentation for Better Few-shot Learning.
Efficient Nearest Neighbor Language Models.
Continual Few-Shot Learning for Text Classification.
Model Selection for Cross-lingual Transfer.
Distributionally Robust Multilingual Machine Translation.
Instance-adaptive training with noise-robust losses against noisy labels.
NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases.
GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks.
Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models.
"Average" Approximates "First Principal Component"? An Empirical Analysis on Representations from Neural Language Models.
Text Counterfactuals via Latent Optimization and Shapley-Guided Search.
The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders.
Human Rationales as Attribution Priors for Explainable Stance Detection.
Comparing Text Representations: A Theory-Driven Approach.
How Do Neural Sequence Models Generalize? Local and Global Cues for Out-of-Distribution Prediction.
Connecting Attributions and QA Model Behavior on Realistic Counterfactuals.
Transformer Feed-Forward Layers Are Key-Value Memories.
Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models.
Toward Deconfounding the Effect of Entity Demographics for Question Answering Accuracy.
Multi-Vector Attention Models for Deep Re-ranking.
PDALN: Progressive Domain Adaptation over a Pre-trained Model for Low-Resource Cross-Domain Named Entity Recognition.
Corpus-based Open-Domain Event Type Induction.
Crosslingual Transfer Learning for Relation and Event Extraction via Word Category and Class Alignments.
Modeling Document-Level Context for Event Detection via Important Context Selection.
Extracting Material Property Measurement Data from Scientific Articles.
Learning from Noisy Labels for Entity-Centric Information Extraction.
ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning.
Incorporating medical knowledge in BERT for clinical relation extraction.
Data Augmentation for Cross-Domain Named Entity Recognition.
Towards Realistic Few-Shot Relation Extraction.
Adversarial Attack against Cross-lingual Knowledge Graph Alignment.
Fine-grained Entity Typing without Knowledge Base.
Unsupervised Paraphrasing Consistency Training for Low Resource Named Entity Recognition.
Modular Self-Supervision for Document-Level Relation Extraction.
Lifelong Event Detection with Knowledge Transfer.
Learning Prototype Representations Across Few-Shot Tasks for Event Detection.
Document-level Entity-based Extraction as Template Generation.
Moving on from OntoNotes: Coreference Resolution Model Transfer.
ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant Supervision.
Learning Constraints and Descriptive Segmentation for Subevent Detection.
The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction.
Refocusing on Relevance: Personalization in NLG.
AESOP: Paraphrase Generation with Adaptive Syntactic Control.
Journalistic Guidelines Aware News Image Captioning.
Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness.
Unsupervised Paraphrasing with Pretrained Language Models.
Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning.
Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation?
Paraphrase Generation: A Survey of the State of the Art.
Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation.
Sentence-Permuted Paragraph Generation.
OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings.
Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources.
Pre-train or Annotate? Domain Adaptation with a Constrained Budget.
Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data.
Improving and Simplifying Pattern Exploiting Training.
Consistent Accelerated Inference via Confident Adaptive Transformers.
Signed Coreference Resolution.
Dialogue State Tracking with a Language Model using Schema-Driven Prompting.
MRF-Chat: Improving Dialogue with Markov Random Fields.
RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging.
SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations.
Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection.
A Label-Aware BERT Attention Network for Zero-Shot Multi-Intent Detection in Spoken Language Understanding.
Multi-Modal Open-Domain Dialogue.
Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts.
Aligning Multidimensional Worldviews and Discovering Ideological Differences.
Improved Latent Tree Induction with Distant Supervision via Span Constraints.
On the Relation between Syntactic Divergence and Zero-Shot Performance.
Genre as Weak Supervision for Cross-lingual Dependency Parsing.
WhyAct: Identifying Action Reasons in Lifestyle Vlogs.
Learning grounded word meaning representations on similarity graphs.
Region under Discussion for visual dialog.
LayoutReader: Pre-training of Text and Layout for Reading Order Detection.
Can Language Models be Biomedical Knowledge Bases?
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy.
Can We Improve Model Robustness through Secondary Attribute Counterfactuals?
AVocaDo: Strategy for Adapting Vocabulary to Downstream Domain.
Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling Approach.
Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT.
Sequential Cross-Document Coreference Resolution.
Extracting Fine-Grained Knowledge Graphs of Scientific Claims: Dataset and Transformer-Based Results.
PRIDE: Predicting Relationships in Conversations.
Enhanced Language Representation with Label Knowledge for Span Extraction.
Fine-grained Entity Typing via Label Reasoning.
Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement.
Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes.
Sociolectal Analysis of Pretrained Language Models.
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer.
Incorporating Residual and Normalization Layers into Analysis of Masked Language Models.
All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality.
Multi-granularity Textual Adversarial Attack with Behavior Cloning.
Lying Through One's Teeth: A Study on Verbal Leakage Cues.
PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation.
We Need to Talk About train-dev-test Splits.
Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions.
CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the Wild.
CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue Summarization.
CHoRaL: Collecting Humor Reaction Labels from Millions of Social Media Users.
The Effect of Round-Trip Translation on Fairness in Sentiment Analysis.
Semantics-Preserved Data Augmentation for Aspect-Based Sentiment Analysis.
Solving Aspect Category Sentiment Analysis as a Text Generation Task.
Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection.
Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification.
Dimensional Emotion Detection from Categorical Emotion.
End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs.
DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation.
CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge Graphs.
Efficient Dialogue Complementary Policy Learning via Deep Q-network Policy and Episodic Memory Policy.
Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems.
Data-to-text Generation by Splicing Together Nearest Neighbors.
Structural Adapters in Pretrained Language Models for AMR-to-Text Generation.
Revisiting Pivot-Based Paraphrase Generation: Language Is Not the Only Optional Pivot.
Generic resources are what you need: Style transfer tasks without task-specific parallel training data.
Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations.
DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer.
Improving Query Graph Generation for Complex Question Answering over Knowledge Base.
End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs.
Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language.
WebSRC: A Dataset for Web-Based Structural Reading Comprehension.
Topic Transferable Table Question Answering.
TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph.
Improving Unsupervised Question Answering via Summarization-Informed Question Generation.
A Unified Encoding of Structures in Transition Systems.
Word Reordering for Zero-shot Cross-lingual Structured Prediction.
Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive Summarization.
Learn to Copy from the Copying History: Correlational Copy Network for Abstractive Summarization.
Transformer-based Lexically Constrained Headline Generation.
Event Graph based Sentence Fusion.
SgSum: Transforming Multi-document Summarization into Sub-graph Selection.
CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Trees.
Frame Semantic-Enhanced Sentence Modeling for Sentence-level Extractive Text Summarization.
Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained Transformer.
How to leverage the multimodal EHR data for better medical prediction?
Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments.
Natural Language Video Localization with Learnable Moment Proposals.
Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization.
Mutual-Learning Improves End-to-End Speech Translation.
Relation-aware Video Reading Comprehension for Temporal Language Grounding.
CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations.
Comparative Opinion Quintuple Extraction from Product Reviews.
Improving Federated Learning for Aspect-based Sentiment Analysis via Topic Memories.
Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble Strategy.
Argument Pair Extraction with Mutual Guidance and Inter-sentence Relation Graph.
Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model.
To be Closer: Learning to Link up Aspects with Opinions.
CATE: A Contrastive Pre-trained Model for Metaphor Detection with Semi-supervised Learning.
Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models.
A Graph-Based Neural Model for End-to-End Frame Semantic Parsing.
TEMP: Taxonomy Expansion with Dynamic Margin Loss through Taxonomy-Paths.
Context-Aware Interaction Network for Question Matching.
Exophoric Pronoun Resolution in Dialogues with Topic Regularization.
Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers.
Aligning Cross-lingual Sentence Representations with Dual Momentum Contrast.
Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution.
WinoLogic: A Zero-Shot Logic-based Diagnostic Dataset for Winograd Schema Challenge.
Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range Context.
COUGH: A Challenge Dataset and Models for COVID-19 FAQ Retrieval.
Constructing a Psychometric Testbed for Fair Natural Language Processing.
Diagnosing the First-Order Logical Reasoning Ability Through LogicNLI.
RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models.
FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale Generation.
FinQA: A Dataset of Numerical Reasoning over Financial Data.
Smoothing Dialogue States for Open Conversational Machine Reading.
Neural Natural Logic Inference for Interpretable Question Answering.
Phrase Retrieval Learns Passage Retrieval, Too.
Large-Scale Relation Learning for Question Answering over Knowledge Bases with Pre-trained Language Models.
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations.
Mapping probability word problems to executable representations.
Adaptive Information Seeking for Open-Domain Question Answering.
Answering Open-Domain Questions of Varying Reasoning Steps from Text.
A Fine-Grained Domain Adaption Model for Joint Word Segmentation and POS Tagging.
Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verification.
Enhancing Document Ranking with Task-adaptive Training and Segmented Token Recovery Mechanism.
Automated Generation of Accurate & Fluent Medical X-ray Reports.
SpellBERT: A Lightweight Pretrained Model for Chinese Spelling Check.
Label-Enhanced Hierarchical Contextualized Representation for Sequential Metaphor Identification.
Leveraging Capsule Routing to Associate Knowledge with Medical Literature Hierarchically.
Biomedical Concept Normalization by Leveraging Hypernyms.
Neuro-Symbolic Reinforcement Learning with First-Order Logic.
Fix-Filter-Fix: Intuitively Connect Any Models for Effective Bug Fixing.
Self-Supervised Curriculum Learning for Spelling Error Correction.
End-to-End Conversational Search for Online Shopping with Utterance Transfer.
Leveraging Order-Free Tag Relations for Context-Aware Recommendation.
Graphine: A Dataset for Graph-aware Terminology Definition Generation.
BPM_MT: Enhanced Backchannel Prediction Model using Multi-Task Learning.
GMH: A General Multi-hop Reasoning Model for KG Completion.
APIRecX: Cross-Library API Recommendation via Pre-Trained Language Model.
What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers.
GraphMR: Graph Neural Network for Mathematical Reasoning.
Improving Math Word Problems with Pre-trained Knowledge and Hierarchical Reasoning.
Cost-effective End-to-end Information Extraction for Semi-structured Document Images.
ActiveEA: Active Learning for Neural Entity Alignment.
STANKER: Stacking Network based on Level-grained Attention-masked BERT for Rumor Detection on Social Media.
Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection.
Self-Supervised Quality Estimation for Machine Translation.
SHAPE : Shifted Absolute Position Embedding for Transformers.
Learning to Rewrite for Non-Autoregressive Neural Machine Translation.
Scheduled Sampling Based on Decoding Steps for Neural Machine Translation.
Improving Neural Machine Translation by Bidirectional Training.
Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation.
Unsupervised Neural Machine Translation with Universal Grammar.
Enlivening Redundant Heads in Multi-head Self-attention for Machine Translation.
Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding.
Recurrent Attention for Neural Machine Translation.
Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-Training.
Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings.
MetaTS: Meta Teacher-Student Network for Multilingual Sequence Labeling with Minimal Supervision.
Natural Language Processing Meets Quantum Physics: A Survey and Categorization.
Beyond Text: Incorporating Metadata and Label Structure for Multi-Label Document Classification using Heterogeneous Graphs.
Re-embedding Difficult Samples via Mutual Information Constrained Semantically Oversampling for Imbalanced Text Classification.
Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution.
HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression.
Frustratingly Simple Pretraining Alternatives to Masked Language Modeling.
kFolden: k-Fold Ensemble for Out-Of-Distribution Detection.
Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification.
Layer-wise Model Pruning based on Mutual Information.
Neuro-Symbolic Approaches for Text-Based Policy Learning.
Scalable Font Reconstruction with Dual Latent Manifolds.
The Power of Scale for Parameter-Efficient Prompt Tuning.
GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning.
Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning.
Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations.
Is this the end of the gold standard? A straightforward reference-less grammatical error correction metric.
Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup.
Explore Better Relative Position Embeddings from Encoding Perspective for Transformer Models.
A Simple and Effective Positional Encoding for Transformers.
Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars.
Linguistic Dependencies and Statistical Dependence.
Lifelong Explainer for Lifelong Learners.
Rethinking Denoised Auto-Encoding in Language Pre-Training.
What's Hidden in a One-layer Randomly Weighted Transformer?
Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little.
A Bayesian Framework for Information-Theoretic Probing.
Relation Extraction with Word Graphs from N-grams.
Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage Retrieval.
From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment.
Dealing with Typos for BERT-based Passage Retrieval and Ranking.
RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking.
Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News Recommendation.
Weakly-supervised Text Classification Based on Keyword Graph.
TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification.
Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder.
Synchronous Dual Network with Cross-Type Attention for Joint Entity and Relation Extraction.
Entity Relation Extraction as Dependency Parsing in Visually Rich Documents.
Low-resource Taxonomy Enrichment with Pretrained Language Models.
Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction.
Importance Estimation from Multiple Perspectives for Keyphrase Extraction.
Machine Reading Comprehension as Data Augmentation: A Case Study on Implicit Event Argument Extraction.
Heterogeneous Graph Neural Networks for Keyphrase Generation.
MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction.
DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling.
An Empirical Study on Multiple Information Sources for Zero-Shot Fine-Grained Entity Typing.
Structure-Augmented Keyphrase Generation.
A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table Filling.
Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification.
Treasures Outside Contexts: Improving Event Detection via Global Statistics.
MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations.
Exploring Task Difficulty for Few-Shot Relation Extraction.
Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data.
Asking Questions Like Educational Experts: Automatically Generating Question-Answer Pairs on Real-World Examination Data.
Iterative GNN-based Decoder for Question Generation.
Building the Directed Semantic Graph for Coherent Long Text Generation.
ConRPG: Paraphrase Generation using Contexts as Regularizer.
Adaptive Bridge between Training and Inference for Dialogue Generation.
Coupling Context Modeling with Zero Pronoun Recovering for Document-Level Natural Language Generation.
Integrating Semantic Scenario and Word Relations for Abstractive Sentence Summarization.
Transductive Learning for Unsupervised Text Style Transfer.
Definition Modelling for Appropriate Specificity.
Evaluating Debiasing Techniques for Intersectional Biases.
FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks.
RankNAS: Efficient Neural Architecture Search by Pairwise Ranking.
Hierarchical Multi-label Text Classification with Horizontal and Vertical Category Correlations.
Multimodal Phased Transformer for Sentiment Analysis.
A Language Model-based Generative Classifier for Sentence-level Discourse Parsing.
Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation.
Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings.
DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings.
EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation Learning.
Transferable Persona-Grounded Dialogues via Grounded Minimal Edits.
Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System.
Unsupervised Conversation Disentanglement through Co-Training.
An Evaluation Dataset and Strategy for Building Robust Multi-turn Response Selection Model.
Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation.
Different Strokes for Different Folks: Investigating Appropriate Further Pre-training Approaches for Diverse Dialogue Tasks.
CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling.
Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks.
More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous Knowledge.
Intention Reasoning Network for Multi-Domain End-to-end Task-Oriented Dialogue.
A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation.
CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue Generation.
Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology Integration.
Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes.
Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems.
Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding.
Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models.
Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?
Visual Goal-Step Inference using wikiHow.
CrossVQA: Scalably Generating Benchmarks for Systematically Testing VQA Generalization.
Reference-Centric Models for Grounded Collaborative Dialogue.
Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning.
You should evaluate your language model on marginal likelihood over tokenisations.
Fast WordPiece Tokenization.
Minimal Supervision for Morphological Inflection.
Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision.
Local Word Discovery for Interactive Transcription.
CRYPTOGRU: Low Latency Privacy-Preserving Text Analysis With GRU.
Fairness-aware Class Imbalanced Learning.
Reconstruction Attack on Instance Encoding for Language Understanding.
Modeling Disclosive Transparency in NLP Application Descriptions.
Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness.
Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search.
Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies.
Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction.
Robust Retrieval Augmented Generation for Zero-shot Slot Filling.
Unsupervised Relation Extraction: A Variational Autoencoder Approach.
AttentionRank: Unsupervised Keyphrase Extraction using Self and Cross Attentions.
"It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation Systems.
Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning.
Contextual Rephrase Detection for Reducing Friction in Dialogue Systems.
Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems.
Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text.
DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization.
CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational Recommendation.
Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning.
Sentence Bottleneck Autoencoders from Transformer Language Models.
Knowledge-Aware Meta-learning for Low-Resource Text Classification.
Competency Problems: On Finding and Removing Artifacts in Language Data.
Foreseeing the Benefits of Incidental Supervision.
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent.
Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation.
Nearest Neighbour Few-Shot Learning for Cross-lingual Classification.
Translation-based Supervision for Policy Generation in Simultaneous Neural Machine Translation.
HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints.
Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech Translation.
Speechformer: Reducing Information Loss in Direct Speech Translation.
Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training.
mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs.
"Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks.
GFST: Gender-Filtered Self-Training for More Accurate Gender in Translation.
Conditional probing: measuring usable information beyond a baseline.
On the Transferability of Adversarial Attacks against Neural Text Classifier.
Contrastive Explanations for Model Interpretability.
Sorting through the noise: Testing robustness of information processing in pre-trained language models.
How much pretraining data do language models need to learn syntax?
Evaluating the Robustness of Neural Language Models to Input Perturbations.
Debiasing Methods in Natural Language Understanding Make Bias More Accessible.
Achieving Model Robustness through Discrete Adversarial Training.
When differential privacy meets NLP: The devil is in the detail.
Shortcutted Commonsense: Data Spuriousness in Deep Learning of Commonsense Reasoning.
ConSeC: Word Sense Disambiguation as Continuous Sense Comprehension.
Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you?
RuleBERT: Teaching Soft Rules to Pre-Trained Language Models.
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders.
Asking It All: Generating Contextualized Questions for any Semantic Role.
Salience-Aware Event Chain Modeling for Narrative Understanding.
Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference.
Narrative Embedding: Re-Contextualization Through Attention.
Weakly supervised discourse segmentation for multiparty oral conversations.
Conundrums in Event Coreference Resolution: Making Sense of the State of the Art.
Understanding Politics via Contextualized Discourse Processing.
MS-Mentions: Consistently Annotating Entity Mentions in Materials Science Procedural Text.
Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer.
AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages.
Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus.
The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation.
A Large-Scale Dataset for Empathetic Response Generation.
Learning Logic Rules for Document-Level Relation Extraction.
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation.
Extend, don't rebuild: Phrasing conditional graph modification as autoregressive sequence labelling.
Label Verbalization and Entailment for Effective Zero and Few-Shot Relation Extraction.
Feedback Attribution for Counterfactual Bandit Learning in Multi-Domain Spoken Language Understanding.
Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLU.
We've had this conversation before: A Novel Approach to Measuring Dialog Similarity.
ConvFiT: Conversational Fine-Tuning of Pretrained Language Models.
Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking.
Detecting Speaker Personas from Conversational Texts.
MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks.
Contrastive Out-of-Distribution Detection for Pretrained Transformers.
ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models.
Certified Robustness to Programmable Transformations in LSTMs.
Relational World Knowledge Representation in Contextual Language Models: A Review.
Neural Attention-Aware Hierarchical Topic Model.
IR like a SIR: Sense-enhanced Information Retrieval for Multiple Languages.
Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval.
Contextualized Query Embeddings for Conversational Search.
Monitoring geometrical properties of word embeddings for detecting the emergence of new topics.
Condenser: a Pre-training Architecture for Dense Retrieval.
Revisiting the Uniform Information Density Hypothesis.
A surprisal-duration trade-off across and within the world's languages.
Frequency Effects on Syntactic Rule Learning in Transformers.
Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining.
Learning Universal Authorship Representations.
CoPHE: A Count-Preserving Hierarchical Evaluation Metric in Large-Scale Multi-Label Text Classification.
Voice Query Auto Completion.
Jump-Starting Item Parameters for Adaptive Language Tests.
Semantic Novelty Detection in Natural Language Descriptions.
Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories.
SELFEXPLAIN: A Self-Explaining Architecture for Neural Text Classifiers.
The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color.
Do Long-Range Language Models Actually Use Long-Range Context?
Exploring the Role of BERT Token Representations to Explain Sentence Probing Results.
Disentangling Representations of Text by Masking Transformers.
The Impact of Positional Encodings on Multilingual Compression.
Learning Compact Metrics for MT.
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation.
Injecting Entity Types into Entity-Guided Text Generation.
Truth-Conditional Captions for Time Series Data.
Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences.
Building Adaptive Acceptability Classifiers for Neural NLG.
Conditional Poisson Stochastic Beams.
Active Learning by Acquiring Contrastive Examples.
Artificial Text Detection via Examining the Topology of Attention Maps.
The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers.
Classification of hierarchical text using geometric deep learning: the case of clinical trials corpus.
Text2Mol: Cross-Modal Molecule Retrieval with Natural Language Queries.
Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data.
Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting.
Open-domain clarification question generation without question examples.
Adversarial Scrubbing of Demographic Information for Text Classification.
Mitigating Language-Dependent Ethnic Bias in BERT.
Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language Models.
Multitask Semi-Supervised Learning for Class-Imbalanced Discourse Classification.
Inducing Stereotypical Character Roles from Plot Structure.
Event Coreference Data (Almost) for Free: Mining Hyperlinks from Online News.
Automatically Exposing Problems with Neural Dialog Models.
Graph Based Network with Contextualized Representations of Turns in Dialogue.
GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation.
Efficient Multi-Task Auxiliary Learning: Selecting Auxiliary Data by Feature Similarity.
SOM-NCSCM : An Efficient Neural Chinese Sentence Compression Model Enhanced with Self-Organizing Map.
Few-Shot Text Generation with Natural Language Instructions.
Dynamic Knowledge Distillation for Pre-trained Language Models.
Distilling Linguistic Context for Language Model Compression.
Latent Hatred: A Benchmark for Understanding Implicit Hate Speech.
How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?
(Mis)alignment Between Stance Expressed in Social Media Data and Public Opinion Surveys.
Narrative Theory for Computational Narrative Understanding.
Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Styles.
Reinforced Counterfactual Data Augmentation for Dual Sentiment Classification.
Progressive Self-Training with Discriminator for Aspect Term Extraction.
Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training.
Improving Multimodal fusion via Mutual Dependency Maximisation.
DILBERT: Customized Pre-Training for Domain Adaptation with Category Shift, with an Application to Aspect Extraction.
Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge.
TEBNER: Domain Specific Named Entity Recognition with Type Expanded Boundary-aware Network.
A Partition Filter Network for Joint Entity and Relation Extraction.
Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification.
Distantly Supervised Relation Extraction using Multi-Layer Revision Network and Confidence-based Multi-Instance Learning.
Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Context.
HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization.
A Thorough Evaluation of Task-Specific Pretraining for Summarization.
Multiplex Graph Neural Network for Extractive Text Summarization.
Decision-Focused Summarization.
Fine-grained Factual Consistency Assessment for Abstractive Summarization Models.
Controllable Neural Dialogue Summarization with Personal Named Entity Planning.
Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining.
Towards Making the Most of Dialogue Characteristics for Neural Chat Translation.
Translating Headers of Tabular Data: A Pilot Study of Schema Translation.
Cross Attention Augmented Transducer Networks for Simultaneous Translation.
ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora.
Zero-Shot Cross-Lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders.
AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translate.
Frontmatter.
