acl 2021 论文列表
Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, Online Event, August 1-6, 2021.
|
Characterizing Social Spambots by their Human Traits.
Could you give me a hint ? Generating inference graphs for defeasible reasoning.
Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification.
Controllable Abstractive Dialogue Summarization with Sketch Supervision.
Cross-document Coreference Resolution over Predicted Mentions.
Knowledge Distillation for Quality Estimation.
Beyond Metadata: What Paper Authors Say About Corpora They Use.
What Did You Refer to? Evaluating Co-References in Dialogue.
DialogSum: A Real-Life Scenario Dialogue Summarization Dataset.
Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs.
Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights.
Phrase-Level Action Reinforcement Learning for Neural Dialog Response Generation.
Highlight-Transformer: Leveraging Key Phrase Aware Attention to Improve Abstractive Multi-Document Summarization.
Automatically Select Emotion for Response via Personality-affected Emotion Transition.
Uncertainty Aware Review Hallucination for Science Article Classification.
Generalized Supervised Attention for Text Generation.
Word Graph Guided Summarization for Radiology Findings.
Slot Transferability for Cross-domain Slot Filling.
Language Models Use Monotonicity to Assess NPI Licensing.
How transfer learning impacts linguistic knowledge in deep NLP models?
Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan.
Rule Augmented Unsupervised Constituency Parsing.
DocNLI: A Large-scale Dataset for Document-level Natural Language Inference.
BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch.
Adapting Monolingual Models: Data can be Scarce when Language Similarity is High.
Enhancing the Open-Domain Dialogue Evaluation in Latent Space.
Climbing the Tower of Treebanks: Improving Low-Resource Dependency Parsing via Hierarchical Source Selection.
Do It Once: An Embarrassingly Simple Joint Matching Approach to Response Selection.
John praised Mary because _he_? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs.
TILGAN: Transformer-based Implicit Latent GAN for Diverse and Coherent Text Generation.
Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation.
Strong and Light Baseline Models for Fact-Checking Joint Inference.
EBERT: Efficient BERT Inference with Dynamic Structured Pruning.
A Multi-Task Approach for Improving Biomedical Named Entity Recognition by Incorporating Multi-Granularity information.
Named Entity Recognition via Noise Aware Training Mechanism with Data Filter.
On the Language Coverage Bias for Neural Machine Translation.
Cross-Domain Review Generation for Aspect-Based Sentiment Analysis.
Multilingual Simultaneous Neural Machine Translation.
BioGen: Generating Biography Summary under Table Guidance on Wikipedia.
What Would a Teacher Do? Predicting Future Talk Moves.
A Text-Centered Shared-Private Framework via Cross-Modal Prediction for Multimodal Sentiment Analysis.
Investigating Memorization of Conspiracy Theories in Text Generation.
As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation.
Use of Formal Ethical Reviews in NLP Literature: Historical Trends and Current Practices.
XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages.
Rule-Aware Reinforcement Learning for Knowledge Graph Reasoning.
Automatic Construction of Sememe Knowledge Bases via Dictionaries.
Analyzing Code Embeddings for Coding Clinical Narratives.
Fingerprinting Fine-tuned Language Models in the Wild.
Semi-Supervised Data Programming with Subset Selection.
HIT - A Hierarchically Fused Deep Attention Network for Robust Code-mixed Language Representation.
Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR.
Revisiting the Evaluation of End-to-end Event Extraction.
PROST: Physical Reasoning about Objects through Space and Time.
Modeling Event-Pair Relations in External Knowledge Graphs for Script Reasoning.
Enhancing Dialogue-based Relation Extraction by Speaker and Trigger Words Prediction.
Using Social and Linguistic Information to Adapt Pretrained Representations for Political Perspective Identification.
Domain-Aware Dependency Parsing for Questions.
Do Grammatical Error Correction Models Realize Grammatical Generalization?
Task-adaptive Pre-training of Language Models with Word Embedding Regularization.
He is very intelligent, she is very beautiful? On Mitigating Social Biases in Language Modelling and Generation.
Constrained Labeled Data Generation for Low-Resource Named Entity Recognition.
Reordering Examples Helps during Priming-based Few-Shot Learning.
Learning to Sample Replacements for ELECTRA Pre-Training.
An Investigation of Suitability of Pre-Trained Language Models for Dialogue Generation - Avoiding Discrepancies.
Exploring Self-Identified Counseling Expertise in Online Support Forums.
Disentangled Code Representation Learning for Multiple Programming Languages.
Plot and Rework: Modeling Storylines for Visual Storytelling.
Inducing Semantic Roles Without Syntax.
Logic-Consistency Text Generation from Semantic Parses.
One Teacher is Enough? Pre-trained Language Model Distillation from Multiple Teachers.
Leveraging Topic Relatedness for Argument Persuasion.
How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation?
Analysis of Tree-Structured Architectures for Code Generation.
Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability.
Benchmarking Neural Topic Models: An Empirical Study.
Verb Sense Clustering using Contextualized Word Representations for Semantic Frame Induction.
Effective Batching for Recurrent Neural Network Grammars.
Modulating Language Models with Emotions.
MLMLM: Link Prediction with Mean Likelihood Masked Language Model.
PSED: A Dataset for Selecting Emphasis in Presentation Slides.
Federated Chinese Word Segmentation with Global Character Associations.
Grounding 'Grounding' in NLP.
Answer Generation for Retrieval-based Question Answering Systems.
On the Copying Behaviors of Pre-Training for Neural Machine Translation.
Memory-Efficient Differentiable Transformer Architecture Search.
Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence.
VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding.
Marked Attribute Bias in Natural Language Inference.
Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring.
SMS Spam Detection Through Skip-gram Embeddings and Shallow Networks.
Prompting Contrastive Explanations for Commonsense Reasoning Tasks.
Unsupervised Label Refinement Improves Dataless Text Classification.
Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?
On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers.
Compositionality of Complex Graphemes in the Undeciphered Proto-Elamite Script using Image and Text Embedding Models.
Effective Attention Sheds Light On Interpretability.
A Formidable Ability: Detecting Adjectival Extremeness with DSMs.
New Dataset and Strong Baselines for the Grammatical Error Correction of Russian.
Who Blames or Endorses Whom? Entity-to-Entity Directed Sentiment Extraction in News Text.
Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation.
HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction.
Analyzing Stereotypes in Generative Text Inference Tasks.
Learning Contextualized Knowledge Structures for Commonsense Reasoning.
Sequence Models for Computational Etymology of Borrowings.
Predicting in-hospital mortality by combining clinical notes with time-series data.
Unsupervised Domain Adaptation for Event Detection using Domain-specific Adapters.
On the Cost-Effectiveness of Stacking of Neural and Non-Neural Methods for Text Classification: Scenarios and Performance Prediction.
The Utility and Interplay of Gazetteers and Entity Segmentation for Named Entity Recognition in English.
Multi-Task Learning and Adapted Knowledge Models for Emotion-Cause Extraction.
Minimally-Supervised Morphological Segmentation using Adaptor Grammars with Linguistic Priors.
Cluster-Former: Clustering-based Sparse Transformer for Question Answering.
Constructing Flow Graphs from Procedural Cybersecurity Texts.
LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer.
Scaling Within Document Coreference to Long Texts.
Perceptual Models of Machine-Edited Text.
Learning Disentangled Latent Topics for Twitter Rumour Veracity Classification.
On the Gap between Adoption and Understanding in NLP.
Leveraging Abstract Meaning Representation for Knowledge Base Question Answering.
Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation.
Differential Privacy for Text Analytics via Natural Text Sanitization.
Explaining NLP Models via Minimal Contrastive Editing (MiCE).
Named Entity Recognition through Deep Representation Learning and Weak Supervision.
Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level.
Assessing the Syntactic Capabilities of Transformer-based Multilingual Language Models.
Using surprisal and fMRI to map the neural bases of broad and local contextual prediction during natural language comprehension.
Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference.
A Non-Autoregressive Edit-Based Approach to Controllable Text Simplification.
Summary Grounded Conversation Generation.
Multimodal Graph-based Transformer Framework for Biomedical Relation Extraction.
On the Lack of Robust Interpretability of Neural Text Classifiers.
Modeling the Unigram Distribution.
Few-Shot Upsampling for Protest Size Detection.
The interplay between language similarity and script on a novel multi-layer Algerian dialect corpus.
Probing Multi-modal Machine Translation with Pre-trained Language Model.
Do Language Models Perform Generalizable Commonsense Inference?
Analyzing Online Political Advertisements.
Detecting Domain Polarity-Changes of Words in a Sentiment Lexicon.
Implications of Using Internet Sting Corpora to Approximate Underage Victims.
Probing Image-Language Transformers for Verb Understanding.
ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language.
Transforming Term Extraction: Transformer-Based Approaches to Multilingual Term Extraction Across Domains.
An Exploratory Analysis of the Relation between Offensive Language and Mental Health.
On the Ethical Limits of Natural Language Processing on Legal Text.
How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation.
Learning Robust Latent Representations for Controllable Speech Synthesis.
Biomedical Interpretable Entity Representations.
It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning.
Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax.
Towards Protecting Vital Healthcare Programs by Extracting Actionable Knowledge from Policy.
Substructure Substitution: Structured Data Augmentation for NLP.
Generating Informative Conclusions for Argumentative Texts.
Annotations Matter: Leveraging Multi-task Learning to Parse UD and SUD.
Multilingual Translation from Denoising Pre-Training.
How well do you know your summarization datasets?
WeaQA: Weak Supervision via Captions for Visual Question Answering.
"We will Reduce Taxes" - Identifying Election Pledges with Language Models.
BERT Busters: Outlier Dimensions that Disrupt Transformers.
AgreeSum: Agreement-Oriented Multi-Document Summarization.
To Point or Not to Point: Understanding How Abstractive Summarizers Paraphrase Text.
Figurative Language in Recognizing Textual Entailment.
Representing Syntax and Composition with Geometric Transformations.
A Joint Model for Structure-based News Genre Classification with Application to Text Summarization.
Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification.
Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering.
Hyperbolic Temporal Knowledge Graph Embeddings with Relational and Time Curvatures.
Neural Entity Recognition with Gazetteer based Fusion.
Grammatical Error Correction as GAN-like Sequence Labeling.
DoT: An efficient Double Transformer for NLP tasks with tables.
BERT-Proof Syntactic Structures: Investigating Errors in Discontinuous Constituency Parsing.
Defending Pre-trained Language Models from Adversarial Word Substitution Without Performance Sacrifice.
Detecting Bot-Generated Text by Characterizing Linguistic Accommodation in Human-Bot Interactions.
SSMix: Saliency-Based Span Mixup for Text Classification.
Is the Lottery Fair? Evaluating Winning Tickets Across Demographics.
Insertion-based Tree Decoding.
Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling.
Manifold Adversarial Augmentation for Neural Machine Translation.
IndoCollex: A Testbed for Morphological Transformation of Indonesian Word Colloquialism.
Dialogue Graph Modeling for Conversational Machine Reading.
Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph.
Probabilistic Graph Reasoning for Natural Proof Generation.
Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment.
Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance.
IgSEG: Image-guided Story Ending Generation.
How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact.
Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference.
Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning.
Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL.
Retrieval Enhanced Model for Commonsense Generation.
Provably Secure Generative Linguistic Steganography.
AugVic: Exploiting BiText Vicinity for Low-Resource NMT.
Probing Pre-Trained Language Models for Disease Knowledge.
Latent Reasoning for Low-Resource Question Generation.
Language Tags Matter for Zero-Shot Neural Machine Translation.
Inspecting the concept knowledge graph encoded by modern language models.
Knowledge-Grounded Dialogue Generation with Term-level De-noising.
Exploring Unsupervised Pretraining Objectives for Machine Translation.
Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction.
On the Interaction of Belief Bias and Explanations.
Modeling the Influence of Verb Aspect on the Activation of Typical Event Locations with BERT.
Hypernym Discovery via a Recurrent Mapping Model.
FrameNet-assisted Noun Compound Interpretation.
On Sparsifying Encoder Outputs in Sequence-to-Sequence Models.
MergeDistill: Merging Language Models using Pre-trained Distillation.
Automatic Rephrasing of Transcripts-based Action Items.
Energy-based Unknown Intent Detection with Data Manipulation.
Learning Sequential and Structural Information for Source Code Summarization.
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?
HacRED: A Large-Scale Relation Extraction Dataset Toward Hard Cases in Practical Applications.
ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation.
Progressive Multi-Granularity Training for Non-Autoregressive Translation.
Detecting Harmful Memes and Their Targets.
Don't Miss the Labels: Label-semantic Augmented Meta-Learner for Few-Shot Text Classification.
Understanding Feature Focus in Multitask Settings for Lexico-semantic Relation Identification.
When Time Makes Sense: A Historically-Aware Approach to Targeted Sense Disambiguation.
Contrastive Aligned Joint Learning for Multilingual Summarization.
Two Parents, One Child: Dual Transfer for Low-Resource Neural Machine Translation.
Transformer-Exclusive Cross-Modal Representation for Vision and Language.
Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation.
Making Flexible Use of Subtasks: A Multiplex Interaction Network for Unified Aspect-based Sentiment Analysis.
Enhancing Language Generation with Effective Checkpoints of Pre-trained Language Model.
GrantRel: Grant Information Extraction via Joint Entity and Relation Extraction.
Dialogue-oriented Pre-training.
A Neural Edge-Editing Approach for Document-Level Relation Graph Extraction.
Automatic Text Simplification for Social Good: Progress and Challenges.
Dynamic and Multi-Channel Graph Convolutional Networks for Aspect-Based Sentiment Analysis.
Paths to Relation Extraction through Semantic Structure.
Graph Relational Topic Model with Higher-order Graph Attention Auto-encoders.
GEM: A General Evaluation Benchmark for Multimodal Tasks.
H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction.
Joint Multi-Decoder Framework with Hierarchical Pointer Network for Frame Semantic Parsing.
Multimodal Fusion with Co-Attention Networks for Fake News Detection.
OKGIT: Open Knowledge Graph Link Prediction with Implicit Types.
AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation.
JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs.
PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning.
Relation Extraction with Type-aware Map Memories of Word Dependencies.
REAM$\sharp$: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation.
Training ELECTRA Augmented with Multi-word Selection.
RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer.
A Multi-Level Attention Model for Evidence-Based Fact Checking.
Dynamic Connected Networks for Chinese Spelling Check.
Stylized Story Generation with Style-Guided Planning.
Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection.
CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection.
Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics.
Event Extraction from Historical Texts: A New Dataset for Black Rebellions.
DocOIE: A Document-level Context-Aware Dataset for OpenIE.
WIND: Weighting Instances Differentially for Model-Agnostic Domain Adaptation.
P-Stance: A Large Dataset for Stance Detection in Political Domain.
A Closer Look into the Robustness of Neural Dependency Parsers Using Better Adversarial Examples.
MA-BERT: Learning Representation by Incorporating Multi-Attribute Knowledge in Transformers.
Confidence-Aware Scheduled Sampling for Neural Machine Translation.
A Multi-Task Learning Framework for Multi-Target Stance Detection.
Leveraging Argumentation Knowledge Graph for Interactive Argument Pair Identification.
Lifelong Learning of Topics and Domain-Specific Word Embeddings.
On the Interplay Between Fine-tuning and Composition in Transformers.
Structure-Aware Pre-Training for Table-to-Text Generation.
Multi-Lingual Question Generation with Language Agnostic Language Model.
Correcting Chinese Spelling Errors with Phonetic Pre-training.
Knowledge-Empowered Representation Learning for Chinese Medical Reading Comprehension: Task, Model and Resources.
Empowering Language Understanding with Counterfactual Reasoning.
Learning Shared Semantic Space for Speech-to-Text Translation.
Neural Combinatory Constituency Parsing.
Assessing Dialogue Systems with Distribution Distances.
Is Human Scoring the Best Criteria for Summary Evaluation?
PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval.
Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement.
Attending via both Fine-tuning and Compressing.
MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers.
Language-based General Action Template for Reinforcement Learning Agents.
Trade the Event: Corporate Events Detection for News-Based Event-Driven Trading.
Automatic Document Sketching: Generating Drafts from Analogous Texts.
Fusion: Towards Automated ICD Coding via Feature Compression.
RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations.
GRICE: A Grammar-based Dataset for Recovering Implicature and Conversational rEasoning.
Are Rotten Apples Edible? Challenging Commonsense Inference Ability with Exceptions.
Entheos: A Multimodal Dataset for Studying Enthusiasm.
Language-Mediated, Object-Centric Representation Learning.
Pipeline Signed Japanese Translation Focusing on a Post-positional Particle Complement and Conjugation in a Low-resource Setting.
Exploring Cross-Lingual Transfer Learning with Unsupervised Machine Translation.
Annotation and Evaluation of Coreference Resolution in Screenplays.
Attention-based Contextual Language Model Adaptation for Speech Recognition.
Evaluating Word Embeddings with Categorical Modularity.
Enhancing Metaphor Detection by Gloss-based Interpretations.
Knowing More About Questions Can Help: Improving Calibration in Question Answering.
Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution.
An Evaluation of Disentangled Representation Learning for Texts.
A Mixed-Method Design Approach for Empirically Based Selection of Unbiased Data Annotators.
End-to-End Self-Debiasing Framework for Robust NLU Training.
Studying the Evolution of Scientific Topics and their Relationships.
Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hate.
End-to-End Construction of NLP Knowledge Graph.
Structured Refinement for Sequential Labeling.
High-Quality Dialogue Diversification by Intermittent Short Extension Ensembles.
"Does it Matter When I Think You Are Lying?" Improving Deception Detection by Integrating Interlocutor's Judgements in Conversations.
Template-Based Named Entity Recognition Using BART.
Alternated Training with Synthetic and Authentic Data for Neural Machine Translation.
Counter-Argument Generation by Attacking Weak Premises.
Cross-Lingual Cross-Domain Nested Named Entity Evaluation on English Web Texts.
CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding.
Gaussian Process based Deep Dyna-Q approach for Dialogue Policy Learning.
How Reliable are Model Diagnostics?
A Query-Driven Topic Model.
KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion.
Fusing Label Embedding into BERT: An Efficient Improvement for Text Classification.
Bi-Granularity Contrastive Learning for Post-Training in Few-Shot Scene.
A Comparison between Pre-training and Large-scale Back-translation for Neural Machine Translation.
Multi-Granularity Contrasting for Cross-Lingual Pre-Training.
Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder.
Improving Unsupervised Extractive Summarization with Facet-Aware Modeling.
Documents Representation via Generalized Coupled Tensor Chain with the Rotation Group constraint.
Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification.
Discriminative Reasoning for Document-level Relation Extraction.
Toward Fully Exploiting Heterogeneous Corpus: A Decoupled Named Entity Recognition Model with Two-stage Training.
Event Detection as Graph Parsing.
BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks.
Target-oriented Fine-tuning for Zero-Resource Named Entity Recognition.
HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management.
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer.
Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning.
Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models.
Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approach.
Making Better Use of Bilingual Information for Cross-Lingual AMR Parsing.
Learning Slice-Aware Representations with Mixture of Attentions.
Learning to Generate Questions by Learning to Recover Answer-containing Sentences.
RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge.
PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support.
UserAdapter: Few-Shot User Learning in Sentiment Analysis.
Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction.
Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning.
BertGCN: Transductive Text Classification by Combining GNN and BERT.
Encouraging Neural Machine Translation to Satisfy Terminology Constraints.
Exploring the Role of Context in Utterance-level Emotion, Act and Intent Classification in Conversations: An Empirical Study.
Jointly Identifying Rhetoric and Implicit Emotions via Multi-Task Learning.
Global Attention Decoder for Chinese Spelling Error Correction.
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters.
Detecting Hallucinated Content in Conditional Neural Sequence Generation.
LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization.
Adversary-Aware Rumor Detection.
MRN: A Locally and Globally Mention-Based Reasoning Network for Document-Level Relation Extraction.
Exploiting Position Bias for Robust Aspect Sentiment Classification.
Incorporating Global Information in Local Attention for Knowledge Representation Learning.
Zero-shot Label-Aware Event Trigger and Argument Classification.
GCRC: A New Challenging MRC Dataset from Gaokao Chinese for Explainable Evaluation.
Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction.
Grammar-Based Patches Generation for Automated Program Repair.
Controlling Text Edition by Changing Answers of Specific Questions.
Enhanced Metaphor Detection via Incorporation of External Knowledge Based on Linguistic Theories.
Grammar-Constrained Neural Semantic Parsing with LR Parsers.
On-the-Fly Attention Modulation for Neural Generation.
Minimax and Neyman-Pearson Meta-Learning for Outlier Languages.
Unsupervised Knowledge Selection for Dialogue Generation.
Survival text regression for time-to-event prediction in conversations.
Unsupervised Energy-based Adversarial Domain Adaptation for Cross-domain Text Classification.
Fusing Context Into Knowledge Graph for Commonsense Question Answering.
Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning.
Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing.
RevCore: Review-Augmented Conversational Recommendation.
Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks?
Learning Algebraic Recombination for Compositional Generalization.
OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding.
Do Explanations Help Users Detect Errors in Open-Domain QA? An Evaluation of Spoken vs. Visual Explanations.
Scheduled Dialog Policy Learning: An Automatic Curriculum Learning Framework for Task-oriented Dialog System.
Code Summarization with Structure-induced Transformer.
Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation.
Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency.
Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering.
Medical Code Assignment with Gated Convolution and Note-Code Interaction.
Frustratingly Simple Few-Shot Slot Tagging.
Sensei: Self-Supervised Sensor Name Segmentation.
Handling Cross- and Out-of-Domain Samples in Thai Word Segmentation.
Why Machine Reading Comprehension Models Learn Shortcuts?
A Survey of Data Augmentation Approaches for NLP.
Predicting cross-linguistic adjective order with information gain.
Promoting Graph Awareness in Linearized Graph-to-Text Generation.
RealFormer: Transformer Likes Residual Attention.
SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification.
Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech.
COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences.
Investigating Text Simplification Evaluation.
What if This Modified That? Syntactic Interventions with Counterfactual Embeddings.
Can Cognate Prediction Be Modelled as a Low-Resource Machine Translation Task?
As Good as New. How to Successfully Recycle English GPT-2 to Make Models for Other Languages.
UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction.
CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation.
Evaluating the Efficacy of Summarization Evaluation across Languages.
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training.
Parallel Attention Network with Sequence Matching for Video Grounding.
Rationalization through Concepts.
Can the Transformer Learn Nested Recursion with Symbol Masking?
Hashing based Efficient Inference for Image-Text Matching.
TransSum: Translating Aspect and Sentiment Embeddings for Self-Supervised Opinion Summarization.
Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking.
Meet The Truth: Leverage Objective Facts and Subjective Views for Interpretable Rumor Detection.
Weakly Supervised Pre-Training for Multi-Hop Retriever.
On Commonsense Cues in BERT for Solving Commonsense Tasks.
Boundary Detection with BERT for Span-level Emotion Cause Analysis.
Prediction or Comparison: Toward Interpretable Qualitative Reasoning.
A Dialogue-based Information Extraction System for Medical Insurance Assessment.
Improving BERT with Syntax-aware Local Attention.
Benchmarking Robustness of Machine Reading Comprehension Models.
Deep Learning against COVID-19: Respiratory Insufficiency Detection in Brazilian Portuguese Speech.
Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots.
TellMeWhy: A Dataset for Answering Why-Questions in Narratives.
Cross-Lingual Transfer in Zero-Shot Cross-Language Entity Linking.
Contrastive Fine-tuning Improves Robustness for Neural Rankers.
Keep the Primary, Rewrite the Secondary: A Two-Stage Approach for Paraphrase Generation.
Better Combine Them Together! Integrating Syntactic Constituency and Dependency Representations for Semantic Role Labeling.
KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction.
SIRE: Separate Intra- and Inter-sentential Reasoning for Document-level Relation Extraction.
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning.
OutFlip: Generating Examples for Unknown Intent Detection with Natural Language Attack.
Error Detection in Large-Scale Natural Language Understanding Systems Using Transformer Models.
DNN-driven Gradual Machine Learning for Aspect-term Sentiment Analysis.
GO FIGURE: A Meta Evaluation of Factuality in Summarization.
Decoupling Adversarial Training for Fair NLP.
Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains.
Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory.
Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation.
AMBERT: A Pre-trained Language Model with Multi-Grained Tokenization.
GLGE: A New General Language Generation Evaluation Benchmark.
Link Prediction on N-ary Relational Facts: A Graph-based Approach.
Relation Classification with Entity Type Restriction.
Using Word Embeddings to Analyze Teacher Evaluations: An Application to a Filipino Education Non-Profit Organization.
XeroAlign: Zero-shot cross-lingual transformer alignment.
LenAtten: An Effective Length Controlling Unit For Text Summarization.
Entity-Aware Abstractive Multi-Document Summarization.
Reader-Guided Passage Reranking for Open-Domain Question Answering.
Spatial Dependency Parsing for Semi-Structured Document Information Extraction.
Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling.
Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning.
Better Chinese Sentence Segmentation with Reinforcement Learning.
O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning.
Contrastive Attention for Automatic Chest X-ray Report Generation.
How does Attention Affect the Model?
Joint Optimization of Tokenization and Downstream Model.
GoG: Relation-aware Graph-over-Graph Network for Visual Dialog.
Deep Cognitive Reasoning Network for Multi-hop Question Answering over Knowledge Graphs.
CoDesc: A Large Code-Description Parallel Dataset.
WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections.
More than just Frequency? Demasking Unsupervised Hypernymy Prediction Methods.
Discovering Topics in Long-tailed Corpora with Causal Intervention.
CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction.
REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training.
Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech.
Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade.
SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics.
More Parameters? No Thanks!
From What to Why: Improving Relation Extraction with Rationale Graph.
The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification.
Semantic Relation-aware Difference Representation Learning for Change Captioning.
Diagnosing Transformers in Task-Oriented Semantic Parsing.
LUX (Linguistic aspects Under eXamination): Discourse Analysis for Automatic Fake News Classification.
Few-Shot Event Detection with Prototypical Amortized Conditional Random Field.
LV-BERT: Exploiting Layer Variety for BERT.
Explainable Inference Over Grounding-Abstract Chains for Science Questions.
