emnlp 2020 论文列表
Findings of the Association for Computational Linguistics: EMNLP 2020, Online Event, 16-20 November 2020.
|
Enhancing Generalization in Natural Language Inference by Syntax.
Weakly-Supervised Modeling of Contextualized Event Embedding for Discourse Relations.
iNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages.
Joint Intent Detection and Entity Linking on Spatial Domain Queries.
Dual Inference for Improving Language Understanding and Generation.
Coming to Terms: Automatic Formation of Neologisms in Hebrew.
Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space.
Paraphrasing vs Coreferring: Two Sides of the Same Coin.
Do Language Embeddings capture Scales?
Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing.
Speaker or Listener? The Role of a Dialogue Agent.
Tensorized Embedding Layers.
Exploiting Unsupervised Data for Emotion Recognition in Conversations.
Robust Backed-off Estimation of Out-of-Vocabulary Embeddings.
Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation.
On the Sub-Layer Functionalities of Transformer Decoder.
Understanding User Resistance Strategies in Persuasive Conversations.
Hierarchical Region Learning for Nested Named Entity Recognition.
Tri-Train: Automatic Pre-Fine Tuning between Pre-Training and Fine-Tuning for SciNER.
TLDR: Extreme Summarization of Scientific Documents.
Probabilistic Case-based Reasoning in Knowledge Bases.
Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory.
ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations.
BERT-QE: Contextualized Query Expansion for Document Re-ranking.
Compressing Transformer-Based Semantic Parsing Models using Compositional Code Embeddings.
Automatic Term Name Generation for Gene Ontology: Task and Dataset.
Learning to Classify Human Needs of Events from Category Definitions with Prototypical Instantiation.
Language-Conditioned Feature Pyramids for Visual Selection Tasks.
Guiding Attention for Self-Supervised Learning with Transformers.
Thinking Like a Skeptic: Defeasible Inference in Natural Language.
MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering.
Multi-hop Question Generation with Graph Convolutional Network.
Exploring BERT's sensitivity to lexical cues using tests from semantic priming.
Byte Pair Encoding is Suboptimal for Language Model Pretraining.
Visuo-Lingustic Question Answering (VLQA) Challenge.
Long Document Ranking with Query-Directed Sparse Transformer.
Structural and Functional Decomposition for Personality Image Captioning in a Communication Game.
Why and when should you pool? Analyzing Pooling in Recurrent Architectures.
The Dots Have Their Values: Exploiting the Node-Edge Connections in Graph-based Neural Models for Document-level Relation Extraction.
Decoding language spatial relations to 2D spatial arrangements.
Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation.
An Empirical Investigation of Beam-Aware Training in Supertagging.
Learning to Learn to Disambiguate: Meta-Learning for Few-Shot Word Sense Disambiguation.
PrivNet: Safeguarding Private Attributes in Transfer Learning for Recommendation.
SMRTer Chatbots: Improving Non-Task-Oriented Dialog with Simulated Multi-Reference Training.
The Pragmatics behind Politics: Modelling Metaphor, Framing and Emotion in Political Discourse.
On the Branching Bias of Syntax Extracted from Pre-trained Language Models.
Improving Limited Labeled Dialogue State Tracking with Self-Supervision.
LIMIT-BERT : Linguistics Informed Multi-Task BERT.
Parsing All: Syntax and Semantics, Dependencies and Spans.
Internal and External Pressures on Language Emergence: Least Effort, Object Constancy and Frequency.
Consistent Response Generation with Controlled Specificity.
Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions.
How Effective is Task-Agnostic Data Augmentation for Pretrained Transformers?
A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies.
Beyond Language: Learning Commonsense from Images for Reasoning.
A Pointer Network Architecture for Joint Morphological Segmentation and Tagging.
Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?
What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models.
BERT for Monolingual and Cross-Lingual Reverse Dictionary.
The birth of Romanian BERT.
Looking inside Noun Compounds: Unsupervised Prepositional and Free Paraphrasing using Language Models.
Training Flexible Depth Model by Multi-Task Learning for Neural Machine Translation.
How Can Self-Attention Networks Recognize Dyck-n Languages?
Detecting Media Bias in News Articles using Gaussian Bias Distributions.
A Shared-Private Representation Model with Coarse-to-Fine Extraction for Target Sentiment Analysis.
Vocabulary Adaptation for Domain Adaptation in Neural Machine Translation.
Contract Discovery: Dataset and a Few-shot Semantic Retrieval Challenge with Competitive Baselines.
Query-Key Normalization for Transformers.
Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information.
Factorized Transformer for Multi-Domain Neural Machine Translation.
Multichannel Generative Language Model: Learning All Possible Factorizations Within and Across Channels.
Assessing Human-Parity in Machine Translation on the Segment Level.
#Turki$hTweets: A Benchmark Dataset for Turkish Text Correction.
Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder.
TinyBERT: Distilling BERT for Natural Language Understanding.
Reference Language based Unsupervised Neural Machine Translation.
No Answer is Better Than Wrong Answer: A Reflection Model for Document Level Machine Reading Comprehension.
Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering.
Towards Low-Resource Semi-Supervised Dialogue Generation with Meta-Learning.
SupMMD: A Sentence Importance Model for Extractive Summarisation using Maximum Mean Discrepancy.
An Empirical Methodology for Detecting and Prioritizing Needs during Crisis Events.
STANDER: An Expert-Annotated Dataset for News Stance Detection and Evidence Retrieval.
A Pilot Study of Text-to-SQL Semantic Parsing for Vietnamese.
Temporal Reasoning in Natural Language Inference.
Large Product Key Memory for Pre-trained Language Models.
Adversarial Training for Code Retrieval with Question-Description Relevance Regularization.
WikiLingua: A New Benchmark Dataset for Multilingual Abstractive Summarization.
Determining Event Outcomes: The Case of #fail.
Effects of Naturalistic Variation in Goal-Oriented Dialog.
NLP Service APIs and Models for Efficient Registration of New Clients.
More Embeddings, Better Sequence Labelers?
Generalizable and Explainable Dialogue Generation via Explicit Action Learning.
Making Information Seeking Easier: An Improved Pipeline for Conversational Search.
Weakly- and Semi-supervised Evidence Extraction.
Finding the Optimal Vocabulary Size for Neural Machine Translation.
MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning.
Towards Context-Aware Code Comment Generation.
Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training.
ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments.
Joint Turn and Dialogue level User Satisfaction Estimation on Mulit-Domain Conversations.
Incremental Text-to-Speech Synthesis with Prefix-to-Prefix Framework.
It's not a Non-Issue: Negation as a Source of Error in Machine Translation.
Event-Related Bias Removal for Real-time Disaster Events.
Inserting Information Bottleneck for Attribution in Transformers.
Question Answering with Long Multiple-Span Answers.
Reevaluating Adversarial Examples in Natural Language.
Modeling Preconditions in Text with a Crowd-sourced Dataset.
Controllable Text Generation with Focused Variation.
Context Analysis for Pre-trained Masked Language Models.
Do Models of Mental Health Based on Social Media Data Generalize?
Generating Accurate EHR Assessment from Medical Graph.
Dr. Summarize: Global Summarization of Medical Dialogue by Exploiting Local Structures.
Denoising Multi-Source Weak Supervision for Neural Text Classification.
Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension.
Document Classification for COVID-19 Literature.
Global Bootstrapping Neural Network for Entity Set Expansion.
Attending to Long-Distance Document Context for Sequence Labeling.
An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems.
Using Visual Feature Space as a Pivot Across Languages.
The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation.
Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction.
Narrative Text Generation with a Latent Discrete Plan.
A Multi-Persona Chatbot for Hotline Counselor Training.
Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher.
Evaluating Factuality in Generation with Dependency-level Entailment.
Approximation of Response Knowledge Retrieval in Knowledge-grounded Dialogue Generation.
Accurate Polyglot Semantic Parsing With DAG Grammars.
Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation.
Resource-Enhanced Neural Model for Event Argument Extraction.
What do we expect from Multiple-choice QA Systems?
Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems.
Unsupervised Domain Adaptation for Cross-lingual Text Labeling.
OCNLI: Original Chinese Natural Language Inference.
Mining Knowledge for Natural Language Inference from Wikipedia Categories.
A Semantics-based Approach to Disclosure Classification in User-Generated Online Content.
UNQOVERing Stereotypical Biases via Underspecified Questions.
Continual Learning for Natural Language Generation in Task-oriented Dialog Systems.
HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification.
Identifying spurious correlations for robust text classification.
BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA.
A Dual-Attention Network for Joint Named Entity Recognition and Sentence Classification of Adverse Drug Events.
On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks.
Document Reranking for Precision Medicine with Neural Matching and Faceted Summarization.
Composed Variational Natural Language Generation for Few-shot Intents.
Improving Event Duration Prediction via Time-aware Pre-training.
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.
What-if I ask you to explain: Explaining the effects of perturbations in procedural text.
A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph.
Improve Transformer Models with Better Relative Position Embeddings.
A Novel Challenge Set for Hebrew Morphological Disambiguation and Diacritics Restoration.
DeSMOG: Detecting Stance in Media On Global Warming.
WER we are and WER we think we are.
Graph-to-Graph Transformer for Transition-based Dependency Parsing.
Regularization of Distinct Strategies for Unsupervised Question Generation.
RobBERT: a Dutch RoBERTa-based Language Model.
Towards Controllable Biases in Language Generation.
Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer.
Towards Zero Shot Conditional Summarization with Adaptive Multi-task Fine-Tuning.
Pushing the Limits of AMR Parsing with Self-Learning.
KoBE: Knowledge-Based Machine Translation Evaluation.
Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning.
Integrating Task Specific Information into Pretrained Language Models for Low Resource Fine Tuning.
An Evaluation Method for Diachronic Word Sense Induction.
A Multilingual View of Unsupervised Machine Translation.
Data Annealing for Informal Language Understanding Tasks.
Towards Domain-Independent Text Structuring Trainable on Large Discourse Treebanks.
Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation.
CLAR: A Cross-Lingual Argument Regularizer for Semantic Role Labeling.
Domain Adversarial Fine-Tuning as an Effective Regularizer.
Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles.
On Long-Tailed Phenomena in Neural Machine Translation.
Adversarial Grammatical Error Correction.
Effective Crowd-Annotation of Participants, Interventions, and Outcomes in the Text of Clinical Trial Reports.
Learning to Generalize for Sequential Decision Making.
Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles.
General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference.
An Instance Level Approach for Shallow Semantic Parsing in Scientific Procedural Text.
A little goes a long way: Improving toxic language classification despite data scarcity.
TurnGPT: a Transformer-based Language Model for Predicting Turn-taking in Spoken Dialog.
Social Commonsense Reasoning with Multi-Head Knowledge Attention.
Assessing Robustness of Text Classification through Maximal Safe Radius Computation.
Cross-Lingual Dependency Parsing by POS-Guided Word Reordering.
DiPair: Fast and Accurate Distillation for Trillion-ScaleText Matching and Pair Modeling.
Contextual Text Style Transfer.
Enhancing Content Planning for Table-to-Text Generation with Data Understanding and Verification.
LEGAL-BERT: "Preparing the Muppets for Court'".
A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder.
Inferring symmetry in natural language.
FENAS: Flexible and Expressive Neural Architecture Search.
Can Pre-training help VQA with Lexical Variations?
Target Conditioning for One-to-Many Generation.
Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem.
Corpora Evaluation and System Bias detection in Multi Document Summarization.
Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs.
LSTMS Compose - and Learn - Bottom-Up.
PharmMT: A Neural Machine Translation Approach to Simplify Prescription Directions.
Improving Word Embedding Factorization for Compression using Distilled Nonlinear Neural Decomposition.
Cross-Lingual Training of Neural Models for Document Ranking.
Be Different to Be Better! A Benchmark to Leverage the Complementarity of Language and Vision.
Learning to Plan and Realize Separately for Open-Ended Dialogue Systems.
Visual Objects As Context: Exploiting Visual Objects for Lexical Entailment.
Universal Dependencies according to BERT: both more specific and more general.
Textual supervision for visually grounded spoken language understanding.
Unsupervised Expressive Rules Provide Explainability and Assist Human Experts Grasping New Domains.
Fine-Grained Grounding for Multimodal Speech Recognition.
Out-of-Sample Representation Learning for Knowledge Graphs.
Extending Multilingual BERT to Low-Resource Languages.
Hierarchical Pre-training for Sequence Labelling in Spoken Dialog.
Toward Stance-based Personas for Opinionated Dialogues.
Fast End-to-end Coreference Resolution for Korean.
An Investigation of Potential Function Designs for Neural CRF.
Learning Numeral Embedding.
Grid Tagging Scheme for End-to-End Fine-grained Opinion Extraction.
Unsupervised Few-Bits Semantic Hashing with Implicit Topics Modeling.
Blockwise Self-Attention for Long Document Understanding.
Abstractive Multi-Document Summarization via Joint Learning with Single-Document Summarization.
Adaptive Feature Selection for End-to-End Speech Translation.
How Does Context Matter? On the Robustness of Event Detection with Context-Selective Mask Generalization.
Zero-shot Entity Linking with Efficient Long Range Sequence Modeling.
On the Interplay Between Fine-tuning and Sentence-Level Probing for Linguistic Knowledge in Pre-Trained Transformers.
Answer Span Correction in Machine Reading Comprehension.
Improving Compositional Generalization in Semantic Parsing.
COSMIC: COmmonSense knowledge for eMotion Identification in Conversations.
On Romanization for Model Transfer Between Scripts in Neural Machine Translation.
Adapting Coreference Resolution to Twitter Conversations.
You could have said that instead: Improving Chatbots with Natural Language Feedback.
Event-Driven Learning of Systematic Behaviours in Stock Markets.
Plug-and-Play Conversational Models.
DivGAN: Towards Diverse Paraphrase Generation via Diversified Generative Adversarial Network.
ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training.
Generalizing Open Domain Fact Extraction and Verification to COVID-FACT thorough In-Domain Language Modeling.
Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems.
Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success.
Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness.
Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximization.
Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation.
MultiDM-GCN: Aspect-Guided Response Generation in Multi-Domain Multi-Modal Dialogue System using Graph Convolution Network.
Guided Dialogue Policy Learning without Adversarial Learning in the Loop.
Recursive Top-Down Production for Sentence Generation with Latent Trees.
Integrating Graph Contextualized Knowledge into Pre-trained Language Models.
A Semi-supervised Approach to Generate the Code-Mixed Text using Pre-trained Encoder and Transfer Learning.
Sparse and Decorrelated Representations for Stable Zero-shot NMT.
Rethinking Topic Modelling: From Document-Space to Term-Space.
Reducing the Frequency of Hallucinated Quantities in Abstractive Summaries.
Reinforcement Learning with Imbalanced Dataset for Data-to-Text Medical Report Generation.
Service-oriented Text-to-SQL Parsing.
Cross-Lingual Suicidal-Oriented Word Embedding toward Suicide Prevention.
The Role of Reentrancies in Abstract Meaning Representation Parsing.
Zero-Shot Rationalization by Multi-Task Transfer Learning from Question Answering.
Computer Assisted Translation with Neural Quality Estimation and Auotmatic Post-Editing.
ConveRT: Efficient and Accurate Conversational Representations from Transformers.
Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages.
Diversify Question Generation with Continuous Content Selectors and Question Type Modeling.
Unsupervised Cross-Lingual Adaptation of Dependency Parsers Using CRF Autoencoders.
TSDG: Content-aware Neural Response Generation with Two-stage Decoding Process.
MedICaT: A Dataset of Medical Images, Captions, and Textual References.
Logic2Text: High-Fidelity Natural Language Generation from Logical Forms.
Extracting Chemical-Protein Interactions via Calibrated Deep Neural Network and Self-training.
KLearn: Background Knowledge Inference from Summarization Data.
Characterizing the Value of Information in Medical Notes.
End-to-End Speech Recognition and Disfluency Removal.
Multi-pretraining for Large-scale Text Classification.
Chunk-based Chinese Spelling Check with Global Optimization.
Focus-Constrained Attention Mechanism for CVAE-based Response Generation.
Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation.
Ruler: Data Programming by Demonstration for Document Labeling.
Automatically Identifying Gender Issues in Machine Translation using Perturbations.
Multi-Turn Dialogue Generation in E-Commerce Platform with the Context of Historical Dialogue.
Scheduled DropHead: A Regularization Method for Transformer Models.
SynET: Synonym Expansion using Transitivity.
Learning Visual-Semantic Embeddings for Reporting Abnormal Findings on Chest X-rays.
Adversarial Subword Regularization for Robust Neural Machine Translation.
PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision.
Pragmatic Issue-Sensitive Image Captioning.
Robust and Interpretable Grounding of Spatial References with Relation Networks.
UnifiedQA: Crossing Format Boundaries With a Single QA System.
No Gestures Left Behind: Learning Relationships between Spoken Language and Freeform Gestures.
Improving End-to-End Bangla Speech Recognition with Semi-supervised Training.
TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising.
On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries.