emnlp 2020 论文列表
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 16-20, 2020.
|
VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles.
Re-evaluating Evaluation in Text Summarization.
Evaluating the Factual Consistency of Abstractive Text Summarization.
Multi-Fact Correction in Abstractive Text Summarization.
On Extractive and Abstractive Neural Document Summarization with Transformer Language Models.
Evaluating and Characterizing Human Rationales.
Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics.
With Little Power Comes Great Responsibility.
An information theoretic view on selecting linguistic probes.
MedDialog: Large-scale Medical Dialogue Datasets.
GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems.
The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection.
A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning.
Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions.
Partially-Aligned Data-to-Text Generation with Distant Supervision.
F\^2-Softmax: Diversifying Neural Text Generation via Frequency Factorized Softmax.
UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation.
Improving Text Generation with Student-Forcing Optimal Transport.
What Can We Learn from Collective Human Opinions on Natural Language Inference Data?
On the Sentence Embeddings from Pre-trained Language Models.
An Analysis of Natural Language Inference Benchmarks through the Lens of Negation.
COGS: A Compositional Generalization Challenge Based on Semantic Interpretation.
What time is it? Temporal Analysis of Novels.
PathQG: Neural Question Generation from Facts.
PyMT5: multi-mode translation of natural language and Python code with transformers.
A State-independent and Time-evolving Network for Early Rumor Detection in Social Media.
Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation.
Neural Topic Modeling with Cycle-Consistent Adversarial Training.
Text Classification Using Label Names Only: A Language Model Self-Training Approach.
Named Entity Recognition Only from Word Embeddings.
Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning.
MIME: MIMicking Emotions for Empathetic Response Generation.
EmoTag1200: Understanding the Association between Emojis and Emotions.
Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning.
Sentiment Analysis of Tweets using Heterogeneous Multi-layer Network Representation and Embedding.
Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations.
Exploring the Role of Argument Structure in Online Debate Persuasion.
CancerEmo: A Dataset for Fine-Grained Emotion Detection.
SRLGRN: Semantic Role Labeling Graph Reasoning Network.
Unsupervised Question Decomposition for Question Answering.
Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning.
A Simple Yet Strong Pipeline for HotpotQA.
Hierarchical Graph Network for Multi-hop Question Answering.
Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube.
Towards Understanding Sample Variance in Visually Grounded Language Generation: Evaluations and Observations.
X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers.
What is More Likely to Happen Next? Video-and-Language Future Event Prediction.
CapWAP: Image Captioning with a Purpose.
Keep CALM and Explore: Language Models for Action Generation in Text-based Games.
Experience Grounds Language.
TeaForN: Teacher-Forcing with N-grams.
Gradient-guided Unsupervised Lexically Constrained Text Generation.
PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation.
Unsupervised Text Style Transfer with Padded Masked Language Models.
POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training.
KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation.
Improving Low Compute Language Modeling with In-Domain Embedding Initialisation.
Incremental Neural Coreference Resolution in Constant Memory.
DualTKB: A Dual Learning Bridge between Text and Knowledge Base.
Knowledge-guided Open Attribute Value Extraction with Reinforcement Learning.
AxCell: Automatic Extraction of Results from Machine Learning Papers.
SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup.
Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction.
Exploring Contextualized Neural Language Models for Temporal Dependency Parsing.
Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning.
Pre-training Mention Representations in Coreference Models.
Revealing the Myth of Higher-Order Inference in Coreference Resolution.
Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks.
Exploring Semantic Capacity of Terms.
Sparsity Makes Sense: Word Sense Disambiguation Using Sparse Contextualized Word Representations.
Sequential Modelling of the Evolution of Word Representations for Semantic Change Detection.
Deconstructing word embedding algorithms.
Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses.
Competence-Level Prediction and Resume & Job Description Matching Using Context-Aware Transformer Models.
To Schedule or not to Schedule: Extracting Task Specific Temporal Entities and Associated Negation Constraints.
Natural Language Processing for Achieving Sustainable Development: the Case of Neural Labelling to Enhance Community Profiling.
Deep Attentive Learning for Stock Movement Prediction From Social Media Text and Company Correlations.
Towards Modeling Revision Requirements in wikiHow Instructions.
NwQM: A neural quality assessment framework for Wikipedia.
Authorship Attribution for Neural Text Generation.
Chapter Captor: Text Segmentation in Novels.
Towards More Accurate Uncertainty Estimation In Text Classification.
META: Metadata-Empowered Weak Supervision for Text Classification.
CoDEx: A Comprehensive Knowledge Graph Completion Benchmark.
Text Graph Transformer for Document Classification.
Evaluating the Calibration of Knowledge Graph Embeddings for Trustworthy Link Prediction.
SynSetExpan: An Iterative Framework for Joint Entity Set Expansion and Synonym Discovery.
Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training.
Precise Task Formalization Matters in Winograd Schema Evaluations.
Multitask Learning for Cross-Lingual Transfer of Broad-coverage Semantic Dependencies.
Data and Representation for Turkish Natural Language Inference.
ConjNLI: Natural Language Inference Over Conjunctive Sentences.
Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start.
The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions.
New Protocols and Negative Results for Textual Entailment Data Collection.
Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference.
Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation.
Information Seeking in the Spirit of Learning: A Dataset for Conversational Curiosity.
INSPIRED: Toward Sociable Recommendation Dialog Systems.
Interview: Large-scale Modeling of Media Dialog with Discourse Patterns and Knowledge Grounding.
doc2dial: A Goal-Oriented Document-Grounded Dialogue Dataset.
Conversational Semantic Parsing for Dialog State Tracking.
Iterative Feature Mining for Constraint-Based Data Collection to Increase Data Diversity and Model Robustness.
Intrinsic Evaluation of Summarization Datasets.
Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles.
MLSUM: The Multilingual Summarization Corpus.
TESA: A Task in Entity Semantic Aggregation for Abstractive Summarization.
A Preliminary Exploration of GANs for Keyphrase Generation.
Effectively pretraining a speech translation decoder with Machine Translation data.
VolTAGE: Volatility Forecasting via Text Audio Fusion with Graph Convolution Networks for Earnings Calls.
The role of context in neural pitch accent detection in English.
The importance of fillers for text representations of speech transcripts.
Vector-Vector-Matrix Architecture: A Novel Hardware-Aware Framework for Low-Latency Inference in NLP Applications.
Transformer Based Multi-Source Domain Adaptation.
Active Learning for BERT: An Empirical Study.
Cold-start Active Learning through Self-supervised Language Modeling.
To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging.
Exploring and Predicting Transferability across NLP Tasks.
Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting.
BERT-of-Theseus: Compressing BERT by Progressive Module Replacing.
On the importance of pre-training data volume for compact language models.
PatchBERT: Just-in-Time, Out-of-Vocabulary Patching.
Entity Linking in 100 Languages.
Constrained Fact Verification for FEVER.
Program Enhanced Fact Verification with Verbalization and Graph Attention Network.
Hierarchical Evidence Set Modeling for Automated Fact Extraction and Verification.
MedFilter: Improving Extraction of Task-relevant Utterances through Integration of Discourse Structure and Ontological Knowledge.
DORB: Dynamically Optimizing Multiple Rewards with Bandits.
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning.
Explainable Automated Fact-Checking for Public Health Claims.
Fortifying Toxic Speech Detectors Against Veiled Toxicity.
Where Are the Facts? Searching for Fact-checked Information to Alleviate the Spread of Fake News.
Weakly Supervised Learning of Nuanced Frames for Analyzing Polarization in News Media.
A Time-Aware Transformer Based Model for Suicide Ideation Detection on Social Media.
Translation Artifacts in Cross-lingual Transfer Learning.
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer.
Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks.
Language Model Prior for Low-Resource Neural Machine Translation.
On the Role of Supervision in Unsupervised Constituency Parsing.
Towards Debiasing NLU Models from Unknown Biases.
Causal Inference of Script Knowledge.
PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge.
Semantic Role Labeling as Syntactic Dependency Parsing.
Fact or Fiction: Verifying Scientific Claims.
Which *BERT? A Survey Organizing Contextualized Encoders.
An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels.
HABERTOR: An Efficient and Effective Deep Hatespeech Detector.
Keeping Up Appearances: Computational Modeling of Face Acts in Persuasion Oriented Discussions.
Centering-based Neural Coherence Modeling with Hierarchical Discourse Segments.
MEGA RST Discourse Treebanks with Structure and Nuclearity from Scalable Distant Sentiment Supervision.
PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction.
"I'd rather just go to bed": Understanding Indirect Answers.
Textual Data Augmentation for Efficient Active Learning on Tiny Datasets.
Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training.
BERT Knows Punta Cana is not just beautiful, it's gorgeous: Ranking Scalar Adjectives with Contextualised Representations.
Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations.
Message Passing for Hyper-Relational Knowledge Graphs.
Debiasing knowledge graph embeddings.
Embedding Words in Non-Vector Space with Unsupervised Graph Learning.
DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion.
A Rigorous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land?
Understanding Procedural Text using Interactive Entity Networks.
Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition.
Neural Conversational QA: Learning to Reason vs Exploiting Patterns.
SLURP: A Spoken Language Understanding Resource Package.
Cross-lingual Spoken Language Understanding with Regularized Representation Alignment.
Probing Pretrained Language Models for Lexical Semantics.
Generationary or "How We Went beyond Word Sense Inventories and Learned to Gloss".
XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization.
Is Graph Structure Necessary for Multi-hop Question Answering?
Coreferential Reasoning Learning for Language Representation.
Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction.
Generating Fact Checking Briefs.
A Knowledge-Aware Sequence-to-Tree Network for Math Word Problem Solving.
DGST: a Dual-Generator Network for Text Style Transfer.
An Unsupervised Joint System for Text Generation from Knowledge Graphs and Semantic Parsing.
On the Ability and Limitations of Transformers to Recognize Formal Languages.
F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering.
Attention is Not Only a Weight: Analyzing Transformers with Vector Norms.
Compositional and Lexical Semantics in RoBERTa, BERT and DistilBERT: A Case Study on CoQA.
Unified Feature and Instance Based Domain Adaptation for Aspect-Based Sentiment Analysis.
Identifying Exaggerated Language.
Diversified Multiple Instance Learning for Document-Level Multi-Aspect Sentiment Classification.
APE: Argument Pair Extraction from Peer Review and Rebuttal via Multi-task Learning.
Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding.
SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge.
Train No Evil: Selective Masking for Task-Guided Pre-Training.
A Multi-Task Incremental Learning Framework with Category Name Embedding for Aspect-Category Sentiment Analysis.
Re-examining the Role of Schema Linking in Text-to-SQL.
Mention Extraction and Linking for SQL Query Generation.
DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset.
"What Do You Mean by That?" A Parser-Independent Interactive Approach for Enhancing Text-to-SQL.
IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation.
An Imitation Game for Learning Semantic Parsers from User Interaction.
Grounded Adaptation for Zero-shot Executable Semantic Parsing.
Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-Trained Language Models.
"You are grounded!": Latent Name Artifacts in Pre-trained Language Models.
What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding.
Learning Music Helps You Read: Using Transfer to Study Linguistic Structure in Language Models.
Pretrained Language Model Embryology: The Birth of ALBERT.
Asking without Telling: Exploring Latent Ontologies in Contextual Representations.
Distilling Structured Knowledge for Text-Based Relational Reasoning.
Dense Passage Retrieval for Open-Domain Question Answering.
Question Directed Graph Attention Network for Numerical Reasoning over Text.
Towards Interpretable Reasoning over Paragraph Effects in Situation.
Multi-hop Inference for Question-driven Summarization.
Multi-Stage Pre-training for Automated Chinese Essay Scoring.
HSCNN: A Hybrid-Siamese Convolutional Neural Network for Extremely Imbalanced Multi-label Text Classification.
MODE-LSTM: A Parameter-efficient Recurrent Network with Multi-Scale for Sentence Classification.
Less is More: Attention Supervision with Counterfactuals for Text Classification.
Multi-resolution Annotations for Emoji Prediction.
Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs.
An Element-aware Multi-representation Model for Law Article Prediction.
Profile Consistency Identification for Open-domain Dialogue Agents.
Continuity of Topic, Interaction, and Query: Learning to Quote in Online Conversations.
Semantic Role Labeling Guided Multi-turn Dialogue ReWriter.
Conundrums in Entity Coreference Resolution: Making Sense of the State of the Art.
MovieChats: Chat like Humans in a Closed Domain.
Regularizing Dialogue Generation by Imitating Implicit Scenarios.
Response Selection for Multi-Party Conversations with Dynamic Topic Tracking.
Personal Information Leakage Detection in Conversations.
Towards Persona-Based Empathetic Conversational Models.
Inquisitive Question Generation for High Level Text Comprehension.
Plan ahead: Self-Supervised Text Planning for Paragraph Completion Task.
MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics.
Template Guided Text Generation for Task-Oriented Dialogue.
Substance over Style: Document-Level Targeted Content Transfer.
STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation.
Generating similes effortlessly like a Pro: A Style Transfer Approach for Simile Generation.
LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention.
Efficient One-Pass End-to-End Entity Linking for Questions.
Design Challenges in Low-resource Cross-lingual Entity Linking.
A Dataset for Tracking Entities in Open Domain Procedural Text.
Scalable Zero-shot Entity Linking with Dense Entity Retrieval.
Entity Enhanced BERT Pre-training for Chinese NER.
Learning Structured Representations of Entity Names using ActiveLearning and Weak Supervision.
Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning.
Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment.
Coarse-to-Fine Pre-training for Named Entity Recognition.
VCDM: Leveraging Variational Bi-encoding and Deep Contextualized Word Representations for Improved Definition Modeling.
Online Conversation Disentanglement with Pointer Networks.
BERT-enhanced Relational Sentence Ordering Network.
Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach.
Better Highlighting: Creating Sub-Sentence Summary Highlights.
Understanding Neural Abstractive Summarization Models via Uncertainty.
Compressive Summarization with Plausibility and Salience Modeling.
Factual Error Correction for Abstractive Summarization Models.
Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation.
A Synset Relation-enhanced Framework with a Try-again Mechanism for Word Sense Disambiguation.
Interpreting Open-Domain Modifiers: Decomposition of Wikipedia Categories into Disambiguated Property-Value Pairs.
When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models.
The Thieves on Sesame Street are Polyglots - Extracting Multilingual Models from Monolingual APIs.
BERT-ATTACK: Adversarial Attack Against BERT Using BERT.
Adversarial Self-Supervised Data-Free Distillation for Text Classification.
BAE: BERT-based Adversarial Examples for Text Classification.
Effective Unsupervised Domain Adaptation with Adversarially Trained Language Models.
Structured Pruning of Large Language Models.
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack.
Autoregressive Knowledge Distillation through Imitation Learning.
Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation.
Structure Aware Negative Sampling in Knowledge Graphs.
Plug and Play Autoencoders for Conditional Text Generation.
Adversarial Semantic Decoupling for Recognizing Open-Vocabulary Slots.
Interpretable Multi-dataset Evaluation for Named Entity Recognition.
DAGA: Data Augmentation with a Generation Approach forLow-resource Tagging Tasks.
Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks.
HIT: Nested Named Entity Recognition via Head-Tail Pair and Token Interaction.
AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network.
XGLUE: A New Benchmark Datasetfor Cross-lingual Pre-training, Understanding and Generation.
Exploiting Sentence Order in Document Alignment.
Interactive Refinement of Cross-Lingual Word Embeddings.
Localizing Open-Ontology QA Semantic Parsers in a Day Using Machine Translation.
CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs.
X-FACTR: Multilingual Factual Knowledge Retrieval from Pretrained Language Models.
OCR Post Correction for Endangered Language Texts.
LAReQA: Language-Agnostic Answer Retrieval from a Multilingual Pool.
Revisiting Modularized Multilingual NMT to Meet Industrial Demands.
Dynamic Data Selection and Weighting for Iterative Back-Translation.
Iterative Domain-Repaired Back-Translation.
Investigating African-American Vernacular English in Transformer-Based Text Generation.
Toward Micro-Dialect Identification in Diaglossic and Code-Switched Environments.
Solving Historical Dictionary Codes with a Neural Language Model.
Multilingual Offensive Language Identification with Cross-lingual Embeddings.
Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning.
Training Question Answering Models From Synthetic Data.
Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space.
AmbigQA: Answering Ambiguous Open-domain Questions.
Inference Strategies for Machine Translation with Conditional Masking.
An Empirical Study of Generation Order for Machine Translation.
Understanding the Difficulty of Training Transformers.
TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion.
Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction.
Knowledge Association with Hyperbolic Knowledge Graph Embeddings.
Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph.
Learning to Pronounce Chinese Without a Pronunciation Dictionary.
RethinkCWS: Is Chinese Word Segmentation a Solved Task?
Measuring the Similarity of Grammatical Gender Systems by Comparing Partitions.
Mind Your Inflections! Improving NLP for Non-Standard Englishes with Base-Inflection Encoding.
Multi-view Story Characterization from Movie Plot Synopses and Reviews.
Deep Weighted MaxSAT for Aspect-based Opinion Extraction.
Affective Event Classification with Discourse-enhanced Self-training.
Inducing Target-Specific Latent Structures for Aspect Sentiment Classification.
Ensemble Distillation for Structured Prediction: Calibrated, Accurate, Fast - Choose Three.
An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks.
Consistency of a Recurrent Language Model With Respect to Incomplete Decoding.
Sequence-Level Mixed Sample Data Augmentation.
Imitation Attacks and Defenses for Black-box Machine Translation Systems.
Digital Voicing of Silent Speech.
Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive Learning.
Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements.
SubjQA: A Dataset for Subjectivity and Review Comprehension.
ISAAQ - Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attention.
Multi-Stage Pre-training for Low-Resource Domain Adaptation.
End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems.
EXAMS: A Multi-subject High School Examinations Dataset for Cross-lingual and Multilingual Question Answering.
How Much Knowledge Can You Pack Into the Parameters of a Language Model?
Severing the Edge Between Before and After: Neural Architectures for Temporal Ordering of Events.
Event Detection: Gate Diversity and Syntactic Importance Scores for Graph Convolution Neural Networks.
CHARM: Inferring Personal Attributes from Conversations.
Introducing a New Dataset for Event Detection in Cybersecurity Texts.
Annotating Temporal Dependency Graphs via Crowdsourcing.
Biomedical Event Extraction as Sequence Labeling.
Weakly Supervised Subevent Knowledge Acquisition.
Writing Strategies for Science Communication: Data and Computational Analysis.
Quantifying Intimacy in Language.
Help! Need Advice on Identifying Advice.
Modeling Protagonist Emotions for Emotion-Aware Storytelling.
A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Support.
IGT2P: From Interlinear Glossed Texts to Paradigms.
Tackling the Low-resource Challenge for Canonical Segmentation.
Automatic Extraction of Rules Governing Morphological Agreement.
COD3S: Diverse Generation with Discrete Semantic Signatures.
Blank Language Models.
Controllable Meaning Representation to Text Generation: Linearization and Data Augmentation Strategies.
Seq2Edits: Sequence Transduction Using Span-level Edit Operations.
CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation.
Facilitating the Communication of Politeness through Fine-Grained Paraphrasing.
Zero-Shot Crosslingual Sentence Simplification.
Sound Natural: Content Rephrasing in Dialog Systems.
Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing.
Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging.
Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference.
End-to-End Slot Alignment and Recognition for Cross-Lingual NLU.
Probing Task-Oriented Dialogue Representation from Language Models.
Conversational Semantic Parsing.
Multilevel Text Alignment with Cross-Document Attention.
Training for Gibbs Sampling on Conditional Random Fields with Neural Scoring Factors.
Semantic Label Smoothing for Sequence to Sequence Problems.
We Can Detect Your Bias: Predicting the Political Ideology of News Articles.
On Losses for Modern Language Models.
Does the Objective Matter? Comparing Training Objectives for Pronoun Resolution.
H2KGAT: Hierarchical Hyperbolic Knowledge Graph Attention Network.
Entities as Experts: Sparse Memory Access with Entity Supervision.
Be More with Less: Hypergraph Attention Networks for Inductive Text Classification.
Analyzing Redundancy in Pretrained Transformer Models.
Assessing Phrasal Representation and Composition in Transformers.
Dissecting Span Identification Tasks with Performance Prediction.
Analyzing Individual Neurons in Pre-trained Language Models.
An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training.
Utility is in the Eye of the User: A Critique of NLP Leaderboards.
Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders.
Unsupervised Cross-Lingual Part-of-Speech Tagging for Truly Low-Resource Scenarios.
Please Mind the Root: Decoding Arborescences for Dependency Parsing.
Unsupervised Parsing via Constituency Tests.
Keep it Surprisingly Simple: A Simple First Order Graph Based Parsing Model for Joint Morphosyntactic Parsing in Sanskrit.
Joint Estimation and Analysis of Risk Behavior Ratings in Movie Scripts.
Modeling the Music Genre Perception across Language-Bound Cultures.
An Empirical Investigation of Contextualized Number Prediction.
Methods for Numeracy-Preserving Word Embeddings.
TNT: Text Normalization based Pre-training of Transformers for Content Moderation.
An Empirical Study of Pre-trained Transformers for Arabic Information Extraction.
RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark.
Text Segmentation by Cross Segment Attention.
BioMegatron: Larger Biomedical Domain Language Model.
Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space.
Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze.
Investigating representations of verb bias in neural language models.
Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models.
Reasoning about Goals, Steps, and Temporal Ordering with WikiHow.
Unsupervised Commonsense Question Answering with Self-Talk.
Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition.
Character-level Representations Improve DRS-based Semantic Parsing Even in the Age of BERT.
GLUCOSE: GeneraLized and COntextualized Story Explanations.
The Multilingual Amazon Reviews Corpus.
Zero-Shot Cross-Lingual Transfer with Meta Learning.
Improving Multilingual Models with Language-Clustered Vocabularies.
A Streaming Approach For Efficient Batched Beam Search.
Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation.
Distilling Multiple Domains for Neural Machine Translation.
From Zero to Hero: On the Limitations of Zero-Shot Language Transfer with Multilingual Transformers.
Do Explicit Alignments Robustly Improve Multilingual Encoders?
Monolingual Adapters for Zero-Shot Neural Machine Translation.
Pre-tokenization of Multi-word Expressions in Cross-lingual Word Embeddings.
On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment.
Identifying Elements Essential for BERT's Multilinguality.
SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning.
Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding.
ALICE: Active Learning with Contrastive Natural Language Explanations.
Visually Grounded Compound PCFGs.
Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts.
Generating Dialogue Responses from a Semantic Latent Space.
Content Planning for Neural Story Generation with Aristotelian Rescoring.
Do sequence-to-sequence VAEs learn global features of sentences?
PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking.
Sparse Text Generation.
Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers.
AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts.
Learning Explainable Linguistic Expressions with Neural Inductive Logic Programming for Sentence Classification.
Adversarial Semantic Collisions.
Ad-hoc Document Retrieval using Weak-Supervision with BERT and GPT2.
Modularized Transfomer-based Ranking Framework.
SLEDGE-Z: A Zero-Shot Baseline for COVID-19 Literature Search.
CLIRMatrix: A massively large collection of bilingual and multilingual datasets for Cross-Lingual Information Retrieval.
Stepwise Extractive Summarization and Planning with Structured Transformers.
Learning to Fuse Sentences with Transformers for Summarization.
Few-Shot Learning for Opinion Summarization.
Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization.
Do "Undocumented Workers" == "Illegal Aliens"? Differentiating Denotation and Connotation in Vector Spaces.
Compositional Demographic Word Embeddings.
Towards Better Context-aware Lexical Semantics: Adjusting Contextualized Representations through Static Anchors.
Improving Word Sense Disambiguation with Translations.
Word Frequency Does Not Predict Grammatical Knowledge in Language Models.
Surprisal Predicts Code-Switching in Chinese-English Bilingual Text.
Investigating Cross-Linguistic Adjective Ordering Tendencies with a Latent-Variable Model.
Speakers Fill Lexical Semantic Gaps with Context.
Human-centric dialog training via offline reinforcement learning.
Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems.
Supervised Seeded Iterated Learning for Interactive Language Learning.
Improving Out-of-Scope Detection in Intent Classification by Using Embeddings of the Word Graph Space of the Classes.
Fast semantic parsing with well-typedness guarantees.
Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling.
X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset.
Leveraging Declarative Knowledge in Text and First-Order Logic for Fine-Grained Propaganda Detection.
Alignment-free Cross-lingual Semantic Role Labeling.
A Joint Multiple Criteria Model in Transfer Learning for Cross-domain Chinese Word Segmentation.
Attention Is All You Need for Chinese Word Segmentation.
DagoBERT: Generating Derivational Morphology with a Pretrained Language Model.
Domain Adaptation of Thai Word Segmentation Models using Stacked Ensemble.
Form2Seq : A Framework for Higher-Order Form Structure Extraction.
Selection and Generation: Learning towards Multi-Product Advertisement Post Generation.
Assessing the Helpfulness of Learning Materials with Inference-Based Learner-Like Agent.
Routing Enforced Generative Model for Recipe Generation.
Neural Topic Modeling by Incorporating Document Relationship Graph.
Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems.
Point to the Expression: Solving Algebraic Word Problems using the Expression-Pointer Transformer Model.
Public Sentiment Drift Analysis Based on Hierarchical Variational Auto-encoder.
OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction.
Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols.
Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations.
Global-to-Local Neural Networks for Document-Level Relation Extraction.
Exposing Shallow Heuristics of Relation Extraction Models with Challenge Data.
Let's Stop Incorrect Comparisons in End-to-end Relation Extraction!
Denoising Relation Extraction from Document-level Distant Supervision.
SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction.
Learning from Context or Names? An Empirical Study on Neural Relation Extraction.
Pre-training for Abstractive Document Summarization by Reinstating Source Text.
Coarse-to-Fine Query Focused Multi-Document Summarization.
Neural Extractive Summarization with Hierarchical Attentive Heterogeneous Graph Network.
Unsupervised Reference-Free Summary Quality Evaluation via Contrastive Learning.
Modeling Content Importance for Summarization with Pre-trained Language Models.
Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis.
Multi-modal Multi-label Emotion Detection with Modality and Label Dependence.
End-to-End Emotion-Cause Pair Extraction based on Sliding Window Multi-Label Learning.
Emotion-Cause Pair Extraction as Sequence Labeling Based on A Novel Tagging Scheme.
Aspect Sentiment Classification with Aspect-Specific Opinion Spans.
Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysis.
Convolution over Hierarchical Syntactic and Lexical Graphs for Aspect Level Sentiment Analysis.
With More Contexts Comes Better Performance: Contextualized Sense Embeddings for All-Round Word Sense Disambiguation.
Within-Between Lexical Relation Classification.
Don't Neglect the Obvious: On the Role of Unambiguous Words in Word Sense Disambiguation.
Task-oriented Domain-specific Meta-Embedding for Text Classification.
Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training.
AttnIO: Knowledge Graph Exploration with In-and-Out Attention Flow for Knowledge-Grounded Dialogue.
Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks.
Task-Completion Dialogue Policy Learning via Monte Carlo Tree Search with Dueling Network.
Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Data.
Counterfactual Off-Policy Training for Neural Dialogue Generation.
Bridging the Gap between Prior and Posterior Knowledge Selection for Knowledge-Grounded Dialogue Generation.
Variational Hierarchical Dialog Autoencoder for Dialog State Tracking Data Augmentation.
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems.
Knowledge-Grounded Dialogue Generation with Pre-trained Language Models.
Sub-Instruction Aware Vision-and-Language Navigation.
The Grammar of Emergent Languages.
VD-BERT: A Unified Vision and Dialog Transformer with BERT.
Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings.
A Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responses.
Learning Physical Common Sense as Knowledge Graph Completion via BERT Data Augmentation and Constrained Tucker Factorization.
Learning to Contrast the Counterfactual Samples for Robust Visual Question Answering.
STL-CQA: Structure-based Transformers with Localization and Encoding for Chart Question Answering.
A Diagnostic Study of Explainability Techniques for Text Classification.
How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking.
Towards Interpreting BERT for Reading Comprehension Based QA.
On the weak link between importance and prunability of attention heads.
When BERT Plays the Lottery, All Tickets Are Winning.
Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks.
Are All Good Word Vector Spaces Isomorphic?
Generating Label Cohesive and Well-Formed Adversarial Claims.
Interpretation of NLP models through input marginalization.
Pareto Probing: Trading Off Accuracy for Complexity.
COMETA: A Corpus for Medical Entity Linking in the Social Media.
Conditional Causal Relationships between Emotions and Causes in Texts.
Incorporating Behavioral Hypotheses for Query Generation.
Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining.
Top-Rank-Focused Adaptive Vote Collection for the Evaluation of Domain-Specific Semantic Models.
A Simple and Effective Model for Answering Multi-span Questions.
Scene Restoring for Narrative Machine Reading Comprehension.
Learning a Cost-Effective Annotation Policy for Question Answering.
Multi-Step Inference for Reasoning Over Paragraphs.
Don't Read Too Much Into It: Adaptive Computation for Open-Domain Question Answering.
Slot Attention with Value Normalization for Multi-Domain Dialogue State Tracking.
BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover's Distance.
Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games.
A Simple Approach to Learning Unsupervised Multilingual Embeddings.
Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains.
Semi-Supervised Bilingual Lexicon Induction with Two-way Interaction.
Disentangle-based Continual Graph Representation Learning.
Word Rotator's Distance.
Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs.
Sparse Parallel Training of Hierarchical Dirichlet Process Topic Models.
Lifelong Language Knowledge Distillation.
Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation.
Multilingual AMR-to-Text Generation.
How to Make Neural Natural Language Generation as Reliable as Templates in Task-Oriented Dialogue.
Homophonic Pun Generation with Lexically Constrained Rewriting.
Improving Grammatical Error Correction Models with Purpose-Built Adversarial Examples.
Incomplete Utterance Rewriting as Semantic Segmentation.
MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models.
Discourse Self-Attention for Discourse Element Identification in Argumentative Student Essays.
QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines.
TED-CDB: A Large-Scale Chinese Discourse Relation Dataset on TED Talks.
Modularized Syntactic Neural Networks for Sentence Classification.
Discontinuous Constituent Parsing as Sequence Labeling.
Some Languages Seem Easier to Parse Because Their Treebanks Leak.
Span-based discontinuous constituency parsing: a family of exact chart-based algorithms with time complexities from O(n\^6) down to O(n\^3).
Parsing Gapping Constructions Based on Grammatical and Semantic Roles.
Can Automatic Post-Editing Improve NMT?
Uncertainty-Aware Semantic Augmentation for Neural Machine Translation.
LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space.
Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT.
COMET: A Neural Framework for MT Evaluation.
Towards Enhancing Faithfulness for Neural Machine Translation.
Losing Heads in the Lottery: Pruning Transformer Attention in Neural Machine Translation.
Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information.
Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias.
CSP: Code-Switching Pre-training for Neural Machine Translation.
Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation.
Direct Segmentation Models for Streaming Speech Translation.
Translation Quality Estimation by Jointly Learning to Score and Rank.
Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages.
Towards Reasonably-Sized Character-Level Transformer NMT by Finetuning Subword Systems.
Self-Induced Curriculum Learning in Self-Supervised Neural Machine Translation.
Reactive Supervision: A New Method for Collecting Sarcasm Data.
HENIN: Learning Heterogeneous Neural Interaction Networks for Explainable Cyberbullying Detection on Social Media.
Comparative Evaluation of Label-Agnostic Selection Bias in Multilingual Hate Speech Datasets.
Suicidal Risk Detection for Military Personnel.
Hate-Speech and Offensive Language Detection in Roman Urdu.
Improving AMR Parsing with Sequence-to-Sequence Pre-training.
XL-AMR: Enabling Cross-Lingual AMR Parsing with Transfer Learning Techniques.
MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale.
Neural Deepfake Detection with Factual Structure of Text.
A Method for Building a Commonsense Inference Dataset based on Basic Events.
Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading.
What do Models Learn from Question Answering Datasets?
Context-Aware Answer Extraction in Question Answering.
AnswerFact: Fact Checking in Product Question Answering.
Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations.
The Secret is in the Spectra: Predicting Cross-lingual Task Performance with Spectral Similarity Measures.
XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning.
Simultaneous Machine Translation with Visual Context.
Position-Aware Tagging for Aspect Sentiment Triplet Extraction.
Adversarial Attack and Defense of Structured Prediction Models.
Uncertainty-Aware Label Refinement for Sequence Labeling.
UDapter: Language Adaptation for Truly Universal Dependency Parsing.
Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages.
Learning Adaptive Segmentation Policy for Simultaneous Translation.
Pronoun-Targeted Fine-tuning for NMT with Hybrid Losses.
Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation.
Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning.
Masking as an Efficient Alternative to Finetuning for Pretrained Language Models.
Exploring Logically Dependent Multi-task Learning with Causal Inference.
Is the Best Better? Bayesian Statistical Model Comparison for Natural Language Processing.
Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning.
If beam search is the answer, what was the question?
Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation.
Retrofitting Structure-aware Transformer Language Model for End Tasks.
A Predicate-Function-Argument Annotation of Natural Language for Open-Domain Information eXpression.
Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product.
FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction.
Enhancing Aspect Term Extraction with Soft Prototypes.
Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News.
Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision.
HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training.
Domain-Specific Lexical Grounding in Noisy Visual-Textual Documents.
MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding.
Visually Grounded Continual Learning of Compositional Phrases.
Detecting Independent Pronoun Bias with Partially-Synthetic Data Generation.
RNNs can generate bounded hierarchical languages with optimal memory.
LOGAN: Local Group Bias Detection by Clustering.
CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models.
An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction.
SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling.
Parallel Interactive Networks for Multi-Domain Dialogue State Generation.
Multi-turn Response Selection using Dialogue Dependency Relations.
Cross Copy Network for Dialogue Generation.
Structured Attention for Unsupervised Dialogue Structure Induction.
GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems.
UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues.
BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues.
Multistage Fusion with Forget Gate for Multimodal Summarization in Open-Domain Videos.
Multimodal Routing: Improving Local and Global Interpretability of Multimodal Language Analysis.
Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection.
CMU-MOSEAS: A Multimodal Language Dataset for Spanish, Portuguese, German and French.
Incorporating Multimodal Information in Open-Domain Web Keyphrase Extraction.
Querying Across Genres for Medical Claims in News.
Short Text Topic Modeling with Topic Distribution Quantization and Negative Sampling Decoder.
Improving Neural Topic Models using Knowledge Distillation.
Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning.
Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!
Beyond [CLS] through Ranking by Generation.
Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders.
Pre-training Entity Relation Encoder with Intra-span and Inter-span Information.
Adaptive Attentional Network for Few-Shot Knowledge Graph Completion.
Knowledge Graph Alignment with Entity-Pair Embedding.
MAVEN: A Massive General Domain Event Detection Dataset.
Event Extraction as Machine Reading Comprehension.
Double Graph Based Reasoning for Document-level Relation Extraction.
Table Fact Verification with Structure-Aware Transformer.
Compositional Phrase Alignment and Beyond.
An Unsupervised Sentence Embedding Method by Mutual Information Maximization.
Semantically Inspired AMR Alignment for the Portuguese Language.
A Bilingual Generative Transformer for Semantic Sentence Embedding.
Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank.
SLM: Learning a Discourse Language Representation with Sentence Unshuffling.
Analogous Process Structure Induction for Sub-event Sequence Prediction.
Benchmarking Meaning Representations in Neural Semantic Parsing.
Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT.
A Knowledge-driven Generative Model for Multi-implication Chinese Medical Procedure Entity Normalization.
Explainable Clinical Decision Support from Text.
Predicting Clinical Trial Results by Implicit Evidence Integration.
Planning and Generating Natural and Diverse Disfluent Texts as Augmentation for Disfluency Detection.
Generating Radiology Reports via Memory-driven Transformer.
Towards Medical Machine Reading Comprehension with Structural Knowledge and Plain Text.
On the Reliability and Validity of Detecting Approval of Political Actors in Tweets.
Social Media Attributions in the Context of Water Crisis.
Coupled Hierarchical Transformer for Stance-Aware Rumor Verification in Social Media Conversations.
Named Entity Recognition for Social Media Texts with Semantic Augmentation.
Hashtags, Emotions, and Comments: A Large-Scale Dataset to Understand Fine-Grained Social Emotions to Online Topics.
Learning from Task Descriptions.
Coding Textual Inputs Boosts the Accuracy of Neural Networks.
Scaling Hidden Markov Language Models.
Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data.
Learning VAE-LDA Models with Rounded Reparameterization Trick.
Improving Bilingual Lexicon Induction for Low Frequency Words.
Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering.
SetConv: A New Approach for Learning from Imbalanced Data.
SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness.
Grounded Compositional Outputs for Adaptive Language Modeling.
Local Additivity Based Data Augmentation for Semi-supervised NER.
Acrostic Poem Generation.
Reading Between the Lines: Exploring Infilling in Visual Narratives.
Online Back-Parsing for AMR-to-Text Generation.
Small but Mighty: New Benchmarks for Split and Rephrase.
ENT-DESC: Entity Description Generation by Exploring Knowledge Graph.
ToTTo: A Controlled Table-To-Text Generation Dataset.
TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions.
Unsupervised Adaptation of Question Answering Systems via Generative Self-training.
IIRC: A Dataset of Incomplete Information Reading Comprehension Questions.
ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning.
Look at the First Sentence: Position Bias in Question Answering.
Non-Autoregressive Machine Translation with Latent Alignments.
Generating Diverse Translation from Model Distribution with Dropout.
Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translation.
Self-Paced Learning for Neural Machine Translation.
Incorporating a Local Translation Mechanism into Non-autoregressive Translation.
On the Sparsity of Neural Machine Translation Models.
Multi-Unit Transformers for Neural Machine Translation.
Token-level Adaptive Training for Neural Machine Translation.
Multi-task Learning for Multilingual Neural Machine Translation.
Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers.
Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation.
Shallow-to-Deep Training for Neural Machine Translation.
Word class flexibility: A deep contextualized approach.
Predicting Reference: What do Language Models Learn about Discourse Models?
Latent Geographical Factors for Analyzing the Evolution of Dialects in Contact.
Filtering Noisy Dialogue Corpora by Connectivity and Content Relatedness.
RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling.
TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue.
Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness.
Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning.
MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering.
Does my multimodal model learn cross-modal interactions? It's harder to tell than you might think!
Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning.
Learning to Represent Image and Text with Denotation Graph.
Where Are You? Localization from Embodied Dialog.
Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning.
PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation.
De-Biased Court's View Generation with Causality.
Reformulating Unsupervised Style Transfer as Paraphrase Generation.
Language Generation with Multi-Hop Reasoning on Commonsense Knowledge Graph.
Semi-supervised New Event Type Induction and Event Detection.
Incremental Event Detection via Knowledge Consolidation Networks.
Joint Constrained Learning for Event-Event Relation Extraction.
Connecting the Dots: Event Graph Schema Induction with Path Language Modeling.
Event Extraction by Answering (Almost) Natural Questions.
Social Chemistry 101: Learning to Reason about Social and Moral Norms.
Measuring Information Propagation in Literary Social Networks.
An Embedding Model for Estimating Legislative Preferences from the Frequency and Sentiment of Tweets.
Condolence and Empathy in Online Communities.
Unsupervised Discovery of Implicit Gender Bias.
ChrEn: Cherokee-English Machine Translation for Endangered Language Revitalization.
Accurate Word Alignment Induction from Neural Machine Translation.
A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT.
Don't Use English Dev: On the Zero-Shot Cross-Lingual Evaluation of Contextual Embeddings.
Efficient Meta Lifelong-Learning with Limited Memory.
Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks.
TernaryBERT: Distillation-aware Ultra-low Bit BERT.
Contrastive Distillation on Intermediate Representations for Language Model Compression.
Friendly Topic Assistant for Transformer Based Abstractive Summarization.
Q-learning with Language Model for Edit-based Unsupervised Summarization.
What Have We Achieved on Text Summarization?
A Spectral Method for Unsupervised Multi-Document Summarization.
AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data.
Cross-Thought for Sentence Encoder Pre-training.
Semantic Evaluation for Text-to-SQL with Distilled Test Suites.
Dialogue Response Ranking Training with Large-Scale Human Feedback Data.
Augmented Natural Language for Generative Sequence Labeling.
Incremental Processing in the Age of Non-Incremental Encoders: An Empirical Assessment of Bidirectional Models for Incremental NLU.
Conversational Document Prediction to Assist Customer Care Agents.
FIND: Human-in-the-Loop Debugging Deep Text Classifiers.
Multi-Dimensional Gender Bias Classification.
Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding.
Calibration of Pre-trained Transformers.
Pre-Training Transformers as Energy-Based Cloze Models.
ETC: Encoding Long and Structured Inputs in Transformers.
KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretations.
Repulsive Attention: Rethinking Multi-head Attention as Bayesian Inference.
Learning Which Features Matter: RoBERTa Acquires a Preference for Linguistic Generalizations (Eventually).
Intrinsic Probing through Dimension Selection.
Information-Theoretic Probing with Minimum Description Length.
A matter of framing: The impact of linguistic formalism on probing results.
More Bang for Your Buck: Natural Perturbation for Robust Question Answering.
Self-Supervised Knowledge Triplet Learning for Zero-Shot Question Answering.
Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering.
PRover: Proof Generation for Interpretable Reasoning over Rules.
Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing.
Simulated multiple reference training improves low-resource machine translation.
Statistical Power and Translationese in Machine Translation Evaluation.
BLEU might be Guilty but References are not Innocent.
Unsupervised stance detection for arguments from consequences.
Quantitative argument summarization and beyond: Cross-domain key point analysis.
Extracting Implicitly Asserted Propositions in Argumentation.
Detecting Attackable Sentences in Arguments.
