emnlp 2021 论文列表
Findings of the Association for Computational Linguistics: EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 16-20 November, 2021.
|
GeDi: Generative Discriminator Guided Sequence Generation.
Making Heads and Tails of Models with Marginal Calibration for Sparse Tagsets.
Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding.
Does Putting a Linguist in the Loop Improve NLU Data Collection?
Improving Unsupervised Commonsense Reasoning Using Knowledge-Enabled Natural Language Inference.
Grammatical Error Correction with Contrastive Learning in Low Error Density Domains.
HOTTER: Hierarchical Optimal Topic Transport with Explanatory Context Representations.
MultiFix: Learning to Repair Multiple Errors by Optimal Alignment Learning.
Incorporating Circumstances into Narrative Event Prediction.
Counter-Contrastive Learning for Language GANs.
'Just What do You Think You're Doing, Dave?' A Checklist for Responsible Data Use in NLP.
Counterfactual Adversarial Learning with Representation Interpolation.
A Divide-And-Conquer Approach for Multi-label Multi-hop Relation Detection in Knowledge Base Question Answering.
Sustainable Modular Debiasing of Language Models.
MAD-G: Multilingual Adapter Generation for Efficient Cross-Lingual Transfer.
Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation.
Perceived and Intended Sarcasm Detection with Graph Attention Networks.
Speculative Sampling in Variational Autoencoders for Dialogue Response Generation.
Stacked AMR Parsing with Silver Data.
Don't Discard All the Biased Instances: Investigating a Core Assumption in Dataset Bias Mitigation Techniques.
A Multi-label Multi-hop Relation Detection Model based on Relation-aware Sequence Generation.
AutoEQA: Auto-Encoding Questions for Extractive Question Answering.
Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate Speech.
Beyond Glass-Box Features: Uncertainty Quantification Enhanced Quality Estimation for Neural Machine Translation.
Data-Efficient Language Shaped Few-shot Image Classification.
Fine-grained Typing of Emerging Entities in Microblogs.
Predicting Anti-Asian Hateful Users on Twitter during COVID-19.
Simple or Complex? Complexity-controllable Question Generation with Soft Templates and Deep Mixture of Experts Model.
Secoco: Self-Correcting Encoding for Neural Machine Translation.
QACE: Asking Questions to Evaluate an Image Caption.
Syntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation.
Comprehensive Punctuation Restoration for English and Polish.
Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework.
ForumSum: A Multi-Speaker Conversation Summarization Dataset.
Aspect-based Sentiment Analysis in Question Answering Forums.
Self-Training using Rules of Grammar for Few-Shot NLU.
Cross-Domain Data Integration for Named Entity Disambiguation in Biomedical Text.
Active Learning for Rumor Identification on Social Media.
Glyph Enhanced Chinese Character Pre-Training for Lexical Sememe Prediction.
Do We Know What We Don't Know? Studying Unanswerable Questions beyond SQuAD 2.0.
KLMo: Knowledge Graph Enhanced Pretrained Language Model with Fine-Grained Relationships.
Co-Teaching Student-Model through Submission Results of Shared Task.
A multilabel approach to morphosyntactic probing.
HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooks.
NICE: Neural Image Commenting with Empathy.
MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets.
Improving Text Auto-Completion with Next Phrase Prediction.
An Exploratory Study on Long Dialogue Summarization: What Works and What's Next.
Competing Independent Modules for Knowledge Integration and Optimization.
Learning Task Sampling Policy for Multitask Learning.
Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates.
Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching.
Block-wise Word Embedding Compression Revisited: Better Weighting and Structuring.
Character-based PCFG Induction for Modeling the Syntactic Acquisition of Morphologically Rich Languages.
Does Vision-and-Language Pretraining Improve Lexical Grounding?
Mitigating Data Poisoning in Text Classification with Differential Privacy.
Task-Oriented Clustering for Dialogues.
FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition.
Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables.
Improved Word Sense Disambiguation with Enhanced Sense Representations.
A Deep Decomposable Model for Disentangling Syntax and Semantics in Sentence Representation.
Reference-based Weak Supervision for Answer Sentence Selection using Web Data.
FCM: A Fine-grained Comparison Model for Multi-turn Dialogue Reasoning.
Discovering Explanatory Sentences in Legal Case Decisions Using Pre-trained Language Models.
Micromodels for Efficient, Explainable, and Reusable Systems: A Case Study on Mental Health.
The Topic Confusion Task: A Novel Evaluation Scenario for Authorship Attribution.
Non-Parametric Unsupervised Domain Adaptation for Neural Machine Translation.
Bag of Tricks for Optimizing Transformer Efficiency.
Cleaning Dirty Books: Post-OCR Processing for Previously Scanned Texts.
Written Justifications are Key to Aggregate Crowdsourced Forecasts.
Want To Reduce Labeling Cost? GPT-3 Can Help.
HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning.
Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding.
Textual Time Travel: A Temporally Informed Approach to Theory of Mind.
NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset.
Probing Commonsense Explanation in Dialogue Response Generation.
ARCH: Efficient Adversarial Regularized Training with Caching.
Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots.
Reconsidering the Past: Optimizing Hidden States in Language Models.
Leveraging Information Bottleneck for Scientific Document Summarization.
Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers.
How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks.
Expected Validation Performance and Estimation of a Random Variable's Maximum.
Graph-Based Decoding for Task Oriented Semantic Parsing.
Multi-task Learning to Enable Location Mention Identification in the Early Hours of a Crisis Event.
Detecting Frames in News Headlines and Lead Images in U.S. Gun Violence Coverage.
Table-based Fact Verification With Salience-aware Learning.
NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions.
Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation.
A Corpus-based Syntactic Analysis of Two-termed Unlike Coordination.
A Plug-and-Play Method for Controlled Text Generation.
Benchmarking Meta-embeddings: What Works and What Does Not.
From None to Severe: Predicting Severity in Movie Scripts.
Neural Unification for Logic Reasoning over Natural Language.
Uncertainty-Aware Machine Translation Evaluation.
Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings.
Convex Aggregation for Opinion Summarization.
Contrastive Document Representation Learning with Graph Attention Networks.
Uncovering Implicit Gender Bias in Narratives through Commonsense Inference.
Parameter-Efficient Domain Knowledge Integration from Multiple Sources for Biomedical Pre-trained Language Models.
Can NLI Models Verify QA Systems' Predictions?
Revisiting Robust Neural Machine Translation: A Transformer Case Study.
Searching for More Efficient Dynamic Programs.
Towards Automatic Bias Detection in Knowledge Graphs.
Retrieval Augmentation Reduces Hallucination in Conversation.
Towards Realistic Single-Task Continuous Learning Research for NER.
Sequence-to-Lattice Models for Fast Translation.
LAMAD: A Linguistic Attentional Model for Arabic Text Diacritization.
ODIST: Open World Classification via Distributionally Shifted Instances.
Adapting Entities across Languages and Cultures.
Distilling Knowledge for Empathy Detection.
Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations.
Post-Editing Extractive Summaries by Definiteness Prediction.
RelDiff: Enriching Knowledge Graph Relation Representations for Sensitivity Classification.
Token-wise Curriculum Learning for Neural Machine Translation.
Gated Transformer for Robust De-noised Sequence-to-Sequence Modelling.
Model-based analysis of brain activity reveals the hierarchy of language in 305 subjects.
Unsupervised Chunking as Syntactic Structure Induction with a Knowledge-Transfer Approach.
Generating Realistic Natural Language Counterfactuals.
TAG: Gradient Attack on Transformer-based Language Models.
Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference.
Do UD Trees Match Mention Spans in Coreference Annotations?
MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding.
Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders.
Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media.
Automatic Bilingual Markup Transfer.
Learning and Analyzing Generation Order for Undirected Sequence Models.
Evidence-based Fact-Checking of Health-related Claims.
A Computational Exploration of Pejorative Language in Social Media.
Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration.
AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models.
MURAL: Multimodal, Multitask Representations Across Languages.
Relation-Guided Pre-Training for Open-Domain Question Answering.
COSMic: A Coherence-Aware Generation Metric for Image Descriptions.
mDAPT: Multilingual Domain Adaptive Pretraining in a Single Model.
SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representations.
Detecting Community Sensitive Norm Violations in Online Conversations.
Modeling Users and Online Communities for Abuse Detection: A Position on Ethics and Explainability.
Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation.
Coreference-aware Surprisal Predicts Brain Response.
Self-Supervised Neural Topic Modeling.
Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence.
The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation.
SD-QA: Spoken Dialectal Question Answering for the Real World.
NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application.
Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data.
SentNoB: A Dataset for Analysing Sentiment on Noisy Bangla Texts.
SciCap: Generating Captions for Scientific Figures.
An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog.
Sometimes We Want Ungrammatical Translations.
Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits.
Does Pretraining for Summarization Require Knowledge Transfer?
Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifiers.
Visual Cues and Error Correction for Translation Robustness.
RW-KD: Sample-wise Loss Terms Re-Weighting for Knowledge Distillation.
Automatic rule generation for time expression normalization.
Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation.
Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens.
Modeling Mathematical Notation Semantics in Academic Papers.
Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model.
Knowledge-Enhanced Evidence Retrieval for Counterargument Generation.
Knowledge Representation Learning with Contrastive Completion Coding.
Locality Preserving Sentence Encoding.
How Does Fine-tuning Affect the Geometry of Embedding Space: A Case Study on Isotropy.
Improving Multilingual Neural Machine Translation with Auxiliary Source Languages.
Data Efficient Masked Language Modeling for Vision and Language.
Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction.
Argumentation-Driven Evidence Association in Criminal Cases.
Comparing learnability of two dependency schemes: 'semantic' (UD) and 'syntactic' (SUD).
Extract, Integrate, Compete: Towards Verification Style Reading Comprehension.
LMSOC: An Approach for Socially Sensitive Pretraining.
MeLT: Message-Level Transformer with Masked Document Representations as Pre-Training for Stance Detection.
A Discourse-Aware Graph Neural Network for Emotion Recognition in Multi-Party Conversation.
Hyperbolic Hierarchy-Aware Knowledge Graph Embedding for Link Prediction.
Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus.
KFCNet: Knowledge Filtering and Contrastive Learning for Generative Commonsense Reasoning.
Lexicon-Based Graph Convolutional Network for Chinese Word Segmentation.
On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation.
Minimizing Annotation Effort via Max-Volume Spectral Sampling.
Knowledge-Interactive Network with Sentiment Polarity Intensity-Aware Multi-Task Learning for Emotion Recognition in Conversations.
Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections.
Automatic Discrimination between Inherited and Borrowed Latin Words in Romance Languages.
"Be nice to your wife! The restaurants are closed": Can Gender Stereotype Detection Improve Sexism Classification?
Progressive Transformer-Based Generation of Radiology Reports.
Counter-Interference Adapter for Multilingual Machine Translation.
Analysis of Language Change in Collaborative Instruction Following.
Open-Domain Contextual Link Prediction and its Complementarity with Entailment Graphs.
Multilingual AMR Parsing with Noisy Knowledge Distillation.
Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition.
A Comprehensive Comparison of Word Embeddings in Event & Entity Coreference Resolution.
AEDA: An Easier Data Augmentation Technique for Text Classification.
Multilingual Translation via Grafting Pre-trained Language Models.
Retrieval Augmented Code Generation and Summarization.
Improving Numerical Reasoning Skills in the Modular Approach for Complex Question Answering on Text.
Adversarial Examples for Evaluating Math Word Problem Solvers.
DialogueTRM: Exploring Multi-Modal Emotional Dynamics in a Conversation.
Controlled Neural Sentence-Level Reframing of News Articles.
Cross-Lingual Leveled Reading Based on Language-Invariant Features.
Patterns of Polysemy and Homonymy in Contextualised Language Models.
CDLM: Cross-Document Language Modeling.
Subword Mapping and Anchoring across Languages.
CodeQA: A Question Answering Dataset for Source Code Comprehension.
Weakly Supervised Semantic Parsing by Learning from Mistakes.
Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graph.
Named Entity Recognition for Entity Linking: What Works and What's Next.
Uncovering the Limits of Text-based Emotion Detection.
Probing Pre-trained Language Models for Semantic Attributes and their Values.
Classification and Geotemporal Analysis of Quality-of-Life Issues in Tenant Reviews.
Beyond Grammatical Error Correction: Improving L1-influenced research writing in English using pre-trained encoder-decoder models.
WikiNEuRal: Combined Neural and Knowledge-based Silver Data Creation for Multilingual NER.
Novel Natural Language Summarization of Program Code via Leveraging Multiple Input Representations.
Informed Sampling for Diversity in Concept-to-Text NLG.
Competence-based Curriculum Learning for Multilingual Machine Translation.
Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation.
Challenges in Detoxifying Language Models.
Give the Truth: Incorporate Semantic Slot into Abstractive Dialogue Summarization.
Attention-based Contrastive Learning for Winograd Schemas.
Skim-Attention: Learning to Focus via Document Layout.
Temporal Adaptation of BERT and Performance on Downstream Document Classification: Insights from Social Media.
Wine is not v i n. On the Compatibility of Tokenizations across Languages.
REBEL: Relation Extraction By End-to-end Language generation.
Refining BERT Embeddings for Document Hashing via Mutual Information Maximization.
What If Sentence-hood is Hard to Define: A Case Study in Chinese Reading Comprehension.
RollingLDA: An Update Algorithm of Latent Dirichlet Allocation to Construct Consistent Time Series from Textual Data.
GiBERT: Enhancing BERT with Linguistic Information using a Lightweight Gated Injection Method.
A Neural Graph-based Local Coherence Model.
Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval.
UniteD-SRL: A Unified Dataset for Span- and Dependency-Based Multilingual and Cross-Lingual Semantic Role Labeling.
MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering.
Generate & Rank: A Multi-task Framework for Math Word Problems.
Attribute Alignment: Controlling Text Generation from Pre-trained Language Models.
Context-aware Entity Typing in Knowledge Graphs.
GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation.
Leveraging Bidding Graphs for Advertiser-Aware Relevance Modeling in Sponsored Search.
Geo-BERT Pre-training Model for Query Rewriting in POI Search.
Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability.
SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks.
Devil's Advocate: Novel Boosting Ensemble Method from Psychological Findings for Text Classification.
Unsupervised Domain Adaptation Method with Semantic-Structural Alignment for Dependency Parsing.
Speaker Turn Modeling for Dialogue Act Classification.
proScript: Partially Ordered Scripts Generation.
Re-entry Prediction for Online Conversations via Self-Supervised Learning.
GenerativeRE: Incorporating a Novel Copy Mechanism and Pretrained Model for Joint Entity and Relation Extraction.
Detecting Polarized Topics Using Partisanship-aware Contextualized Topic Embeddings.
On the Effects of Transformer Size on In- and Out-of-Domain Calibration.
Are Factuality Checkers Reliable? Adversarial Meta-evaluation of Factuality in Summarization.
Compositional Data and Task Augmentation for Instruction Following.
Few-Shot Novel Concept Learning for Semantic Parsing.
Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehension.
Mitigating Data Scarceness through Data Synthesis, Augmentation and Curriculum for Abstractive Summarization.
Natural SQL: Making SQL Easier to Infer from Natural Language Specifications.
Say 'YES' to Positivity: Detecting Toxic Language in Workplace Communications.
TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation.
Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning.
DIRECT: Direct and Indirect Responses in Conversational Text Corpus.
Span Fine-tuning for Pre-trained Language Models.
Retrieve, Discriminate and Rewrite: A Simple and Effective Framework for Obtaining Affective Response in Retrieval-Based Chatbots.
An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling.
Grouped-Attention for Content-Selection and Content-Plan Generation.
Japanese Zero Anaphora Resolution Can Benefit from Parallel Texts Through Neural Transfer Learning.
ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts.
Translation as Cross-Domain Knowledge: Attention Augmentation for Unsupervised Cross-Domain Segmenting and Labeling Tasks.
Language Resource Efficient Learning for Captioning.
Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing.
RoR: Read-over-Read for Long Document Machine Reading Comprehension.
A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base.
Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser.
Grounded Graph Decoding improves Compositional Generalization in Question Answering.
UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings.
WIKIBIAS: Detecting Multi-Span Subjective Biases in Language.
fBERT: A Neural Transformer for Identifying Offensive Content.
Semantic Alignment with Calibrated Similarity for Multilingual Sentence Embedding.
An Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysis.
Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation.
"Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding.
APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing.
When in Doubt: Improving Classification Performance with Alternating Normalization.
Sent2Span: Span Detection for PICO Extraction in the Biomedical Text without Span Annotations.
Optimal Neural Program Synthesis from Multimodal Specifications.
TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling.
Improving Dialogue State Tracking with Turn-based Loss Function and Sequential Data Augmentation.
Conical Classification For Efficient One-Class Topic Determination.
Exploring Multitask Learning for Low-Resource Abstractive Summarization.
Char2Subword: Extending the Subword Embedding Space Using Robust Character Compositionality.
BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks.
Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework.
ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection.
Profiling News Discourse Structure Using Explicit Subtopic Structures Guided Critics.
HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge.
Rethinking Sentiment Style Transfer.
A Conditional Generative Matching Model for Multi-lingual Reply Suggestion.
MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization.
Entity-Based Semantic Adequacy for Data-to-Text Generation.
Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning.
Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph.
Don't Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting.
SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation.
An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solving.
Topic-Guided Abstractive Multi-Document Summarization.
Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning.
Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving.
EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation.
Inconsistency Matters: A Knowledge-guided Dual-inconsistency Network for Multi-modal Rumor Detection.
Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model.
EventKE: Event-Enhanced Knowledge Graph Embedding.
End-to-end Neural Information Status Classification.
Constructing contrastive samples via summarization for text classification with limited annotations.
A Finer-grain Universal Dialogue Semantic Structures based Model For Abstractive Dialogue Summarization.
Generalization in Text-based Games via Hierarchical Reinforcement Learning.
Self Question-answering: Aspect-based Sentiment Analysis by Role Flipped Machine Reading Comprehension.
Multilingual Neural Machine Translation: Can Linguistic Hierarchies Help?
EDTC: A Corpus for Discourse-Level Topic Chain Parsing.
Improving End-to-End Task-Oriented Dialog System with A Simple Auxiliary Task.
Combining Curriculum Learning and Knowledge Distillation for Dialogue Generation.
CVAE-based Re-anchoring for Implicit Discourse Relation Classification.
Which is Making the Contribution: Modulating Unimodal and Cross-modal Dynamics for Multimodal Sentiment Analysis.
ArabicTransformer: Efficient Large Arabic Language Model with Funnel Transformer and ELECTRA Objective.
TWT: Table with Written Text for Controlled Data-to-Text Generation.
Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization.
An unsupervised framework for tracing textual sources of moral change.
Past, Present, and Future: Conversational Emotion Recognition through Structural Modeling of Psychological Knowledge.
Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions.
Learning and Evaluating a Differentially Private Pre-trained Language Model.
Neural Media Bias Detection Using Distant Supervision With BABE - Bias Annotations By Experts.
Winnowing Knowledge for Multi-choice Question Answering.
Exploiting Reasoning Chains for Multi-hop Science Question Answering.
Learning to Answer Psychological Questionnaire for Personality Detection.
Improving Abstractive Dialogue Summarization with Hierarchical Pretraining and Topic Segment.
Effectiveness of Pre-training for Few-shot Intent Classification.
Less Is More: Domain Adaptation with Lottery Ticket for Reading Comprehension.
KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals.
Learning to Ground Visual Objects for Visual Dialog.
Entity-level Cross-modal Learning Improves Multi-modal Machine Translation.
Diversity and Consistency: Exploring Visual Question-Answer Pair Generation.
Exploring Decomposition for Table-based Fact Verification.
Towards Document-Level Paraphrase Generation with Sentence Rewriting and Reordering.
Compositional Generalization via Semantic Tagging.
CNNBiF: CNN-based Bigram Features for Named Entity Recognition.
Task-adaptive Pre-training and Self-training are Complementary for Natural Language Understanding.
Structured abbreviation expansion in context.
When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions.
Calibrate your listeners! Robust communication-based training for pragmatic speakers.
To Protect and To Serve? Analyzing Entity-Centric Framing of Police Violence.
Towards Improving Adversarial Training of NLP Models.
Robust Fragment-Based Framework for Cross-lingual Sentence Retrieval.
Exploiting Curriculum Learning in Unsupervised Neural Machine Translation.
Leveraging Word-Formation Knowledge for Chinese Word Sense Disambiguation.
Few-Shot Table-to-Text Generation with Prototype Memory.
Plan-then-Generate: Controlled Data-to-Text Generation via Planning.
Discovering Representation Sprachbund For Multilingual Pre-Training.
What Does Your Smile Mean? Jointly Detecting Multi-Modal Sarcasm and Sentiment Using Quantum Probability.
R2-D2: A Modular Baseline for Open-Domain Question Answering.
Knowledge-Guided Paraphrase Identification.
Probing Across Time: What Does RoBERTa Know and When?
Improving Empathetic Response Generation by Recognizing Emotion Cause in Conversations.
An Uncertainty-Aware Encoder for Aspect Detection.
Recall and Learn: A Memory-augmented Solver for Math Word Problems.
Learning Hard Retrieval Decoder Attention for Transformers.
Recommend for a Reason: Unlocking the Power of Unsupervised Aspect-Sentiment Co-Extraction.
How to Select One Among All ? An Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding.
An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces.
Efficient Test Time Adapter Ensembling for Low-resource Language Varieties.
Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning.
Rethinking Why Intermediate-Task Fine-Tuning Works.
How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning.
Stream-level Latency Evaluation for Simultaneous Machine Translation.
FANATIC: FAst Noise-Aware TopIc Clustering.
Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society.
Saliency-based Multi-View Mixed Language Training for Zero-shot Cross-lingual Classification.
Detecting Compositionally Out-of-Distribution Examples in Semantic Parsing.
Casting the Same Sentiment Classification Problem.
Distantly Supervised Relation Extraction in Federated Settings.
Bidirectional Hierarchical Attention Networks based on Document-level Context for Emotion Cause Extraction.
Unseen Entity Handling in Complex Question Answering over Knowledge Base via Language Generation.
Distilling Word Meaning in Context from Pre-trained Language Models.
Effect Generation Based on Causal Reasoning.
Using Question Answering Rewards to Improve Abstractive Summarization.
Improving Knowledge Graph Embedding Using Affine Transformations of Entities Corresponding to Each Relation.
Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning.
Semi-supervised Relation Extraction via Incremental Meta Self-Training.
CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade.
Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings.
Multilingual Chart-based Constituency Parse Extraction from Pre-trained Language Models.
BFClass: A Backdoor-free Text Classification Framework.
Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions.
GooAQ: Open Question Answering with Diverse Answer Types.
Beyond Reptile: Meta-Learned Dot-Product Maximization between Gradients for Improved Single-Task Regularization.
Cartography Active Learning.
P-INT: A Path-based Interaction Model for Few-shot Knowledge Graph Completion.
WHOSe Heritage: Classification of UNESCO World Heritage Statements of "Outstanding Universal Value" with Soft Labels.
A Model of Cross-Lingual Knowledge-Grounded Response Generation for Open-Domain Dialogue Systems.
Exploring Sentence Community for Document-Level Event Extraction.
Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer.
An Alignment-Agnostic Model for Chinese Text Error Correction.
Mixup Decoding for Diverse Machine Translation.
Self-Attention Graph Residual Convolutional Networks for Event Detection with dependency relations.
Mining the Cause of Political Decision-Making from Social Media: A Case Study of COVID-19 Policies across the US States.
Multi-Task Dense Retrieval via Model Uncertainty Fusion for Open-Domain Question Answering.
Discourse-Based Sentence Splitting.
TWEETSUMM - A Dialog Summarization Dataset for Customer Service.
WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach.
An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languages.
Compositional Networks Enable Systematic Generalization for Grounded Language Understanding.
Visually Grounded Concept Composition.
Dense Hierarchical Retrieval for Open-domain Question Answering.
Segmenting Natural Language Sentences via Lexical Unit Analysis.
Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable.
Euphemistic Phrase Detection by Masked Language Model.
Generating Mammography Reports from Multi-view Mammograms with BERT.
Improving Privacy Guarantee and Efficiency of Latent Dirichlet Allocation Model Training Under Differential Privacy.
Improving Embedding-based Large-scale Retrieval via Label Enhancement.
HiTRANS: A Hierarchical Transformer Network for Nested Named Entity Recognition.
Cross-Modal Retrieval Augmentation for Multi-Modal Classification.
Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation.
Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Grounding.
Joint Multimedia Event Extraction from Video and Article.
A Web Scale Entity Extraction System.
Self-Teaching Machines to Read and Comprehend with Large-Scale Multi-Subject Question-Answering Data.
Neural News Recommendation with Collaborative News Encoding and Structural User Encoding.
Language Clustering for Multilingual Named Entity Recognition.
Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering.
Extracting Topics with Simultaneous Word Co-occurrence and Semantic Correlation Graphs: Neural Topic Modeling for Short Texts.
K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce.
Frontmatter.
