acl 2020 论文列表
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020.
|
Treebank Embedding Vectors for Out-of-domain Dependency Parsing.
SeqVAT: Virtual Adversarial Training for Semi-Supervised Sequence Labeling.
Revisiting Higher-Order Dependency Parsers.
Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches.
Uncertain Natural Language Inference.
Towards Robustifying NLI Models Against Lexical Dataset Biases.
QuASE: Question-Answer Driven Sentence Encoding.
NILE : Natural Language Inference with Faithful Natural Language Explanations.
Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance.
End-to-End Bias Mitigation by Modelling Biases in Corpora.
Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition.
Smart To-Do: Automatic Generation of To-Do Items from Emails.
Should All Cross-Lingual Embeddings Speak English?
ScriptWriter: Narrative-Guided Script Generation.
Predicting Performance for Natural Language Processing Tasks.
Multi-Label and Multilingual News Framing Analysis.
Let Me Choose: From Verbal Context to Font Selection.
DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking.
Clinical Concept Linking with Contextualized Neural Representations.
Automated Topical Component Extraction Using Neural Network Attention Scores from Source-based Essay Scoring.
A Multi-Perspective Architecture for Semantic Code Search.
Regularized Context Gates on Transformer for Machine Translation.
Parallel Corpus Filtering via Pre-trained Language Models.
Evaluating Robustness to Input Perturbations for Neural Machine Translation.
Balancing Training for Multilingual Neural Machine Translation.
Addressing Posterior Collapse with Mutual Information for Improved Variational Neural Machine Translation.
TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition.
TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product Categories.
Multi-Domain Named Entity Recognition with Genre-Aware and Agnostic Inference.
Hierarchical Entity Typing via Multi-level Learning to Rank.
A Generate-and-Rank Framework with Semantic Type Regularization for Biomedical Concept Normalization.
Unsupervised Cross-lingual Representation Learning at Scale.
Universal Decompositional Semantic Parsing.
TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data.
Structured Tuning for Semantic Role Labeling.
Predicting the Focus of Negation: Model and Error Analysis.
Exploring Unexplored Generalization Challenges for Cross-Database Semantic Parsing.
Estimating Mutual Information Between Dense Word Embeddings.
Don't Stop Pretraining: Adapt Language Models to Domains and Tasks.
Beyond Possession Existence: Duration and Co-Possession.
Active Learning for Coreference Resolution using Discrete Annotation.
Phonetic and Visual Priors for Decipherment of Informal Romanization.
Joint Diacritization, Lemmatization, Normalization, and Fine-Grained Morphological Tagging.
Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge.
Improving Chinese Word Segmentation with Wordhood Memory Networks.
Frugal Paradigm Completion.
A Multitask Learning Approach for Diacritic Restoration.
Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting.
TVQA+: Spatio-Temporal Grounding for Video Question Answering.
Mapping Natural Language Instructions to Mobile UI Action Sequences.
History for Visual Dialog: Do we really need it?
A negative case analysis of visual grounding methods for VQA.
Feature Projection for Improved Text Classification.
Empower Entity Set Expansion via Language Model Probing.
CluHTM - Semantic Hierarchical Topic Modeling based on CluWords.
A Prioritization Model for Suicidality Risk Assessment.
Soft Gazetteers for Low-Resource Named Entity Recognition.
ZeroShotCeres: Zero-Shot Relation Extraction from Semi-Structured Webpages.
Sources of Transfer in Multilingual Named Entity Recognition.
Rationalizing Medical Relation Prediction from Corpus-level Statistics.
Multi-Sentence Argument Linking.
Learning Interpretable Relationships between Entities, Relations and Concepts via Bayesian Structure Learning on Open Domain Facts.
From English to Code-Switching: Transfer Learning with Strong Morphological Clues.
Exploiting the Syntax-Model Consistency for Neural Relation Extraction.
Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding.
A Joint Neural Model for Information Extraction with Global Features.
Structural Information Preserving for Graph-to-Text Generation.
R^3: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge.
One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases.
Neural CRF Model for Sentence Alignment in Text Simplification.
Logical Natural Language Generation from Open-Domain Tables.
Iterative Edit-Based Unsupervised Sentence Simplification.
ESPRIT: Explaining Solutions to Physical Reasoning Tasks.
Distilling Knowledge Learned in BERT for Text Generation.
BLEURT: Learning Robust Metrics for Text Generation.
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension.
Gender Gap in Natural Language Processing Research: Disparities in Authorship and Citations.
To Test Machine Comprehension, Start by Defining Comprehension.
Returning the N to NLP: Towards Contextually Personalized Classification Models.
On Forgetting to Cite Older Papers: An Analysis of the ACL Anthology.
Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly.
Automated Evaluation of Writing - 50 Years and Counting.
Supervised Grapheme-to-Phoneme Conversion of Orthographic Schwas in Hindi and Punjabi.
The Paradigm Discovery Problem.
Variational Neural Machine Translation with Normalizing Flows.
Using Context in Neural Machine Translation Training Objectives.
Unsupervised Domain Clusters in Pretrained Language Models.
Translationese as a Language in "Multilingual" NMT.
Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem.
Learning a Multi-Domain Curriculum for Neural Machine Translation.
In Neural Machine Translation, What Does Transfer Learning Transfer?
Hard-Coded Gaussian Attention for Neural Machine Translation.
HAT: Hardware-Aware Transformers for Efficient Natural Language Processing.
Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning.
Learning Web-based Procedures by Reasoning over Explanations and Demonstrations in Context.
Cross-Modality Relevance for Reasoning on Language and Vision.
CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning.
Towards Open Domain Event Trigger Identification using Adversarial Domain Adaptation.
Temporally-Informed Analysis of Named Entity Recognition.
The Sensitivity of Language Models and Humans to Winograd Schema Perturbations.
Temporal Common Sense Acquisition with Minimal Supervision.
RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers.
Good-Enough Compositional Data Augmentation.
Non-Linear Instance-Based Cross-Lingual Mapping for Non-Isomorphic Embedding Spaces.
Understanding Advertisements with BERT.
Improving Disentangled Text Representation Learning with Information-Theoretic Guidance.
Do Transformers Need Deep Long-Range Memory?
Contrastive Self-Supervised Learning for Commonsense Reasoning.
SciREX: A Challenge Dataset for Document-Level Information Extraction.
Revisiting Unsupervised Relation Extraction.
Machine Reading of Historical Events.
A Two-Step Approach for Implicit Event Argument Detection.
Toward Better Storylines with Sentence-Level Language Models.
Shape of Synth to Come: Why We Should Use Synthetic Data for English Surface Realization.
Improving Image Captioning with Better Use of Caption.
What are the Goals of Distributional Semantics?
What Question Answering can Learn from Trivia Nerds.
Speech Translation and the End-to-End Promise: Taking Stock of Where We Are.
From SPMRL to NMRL: What Did We Learn (and Unlearn) in a Decade of Parsing Morphologically-Rich Languages (MRLs)?
A Tale of a Probe and a Parser.
A Call for More Rigor in Unsupervised Cross-lingual Learning.
Premise Selection in Natural Language Mathematical Texts.
Generating Fact Checking Explanations.
Fine-grained Fact Verification with Kernel Graph Attention Network.
Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering.
MLQA: Evaluating Cross-lingual Extractive Question Answering.
DoQA - Accessing Domain-Specific FAQs via Conversational QA.
ClarQ: A large-scale and diverse dataset for Clarification Question Generation.
Semi-supervised Contextual Historical Text Normalization.
Predicting the Growth of Morphological Families from Social and Linguistic Factors.
2kenize: Tying Subword Sequences for Chinese Script Conversion.
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection.
Effective Estimation of Deep Generative Language Models.
CamemBERT: a Tasty French Language Model.
Refer360$^\circ$: A Referring Expression Recognition Dataset in 360$^\circ$ Images.
Multimodal Neural Graph Memory Networks for Visual Question Answering.
Aligned Dual Channel Graph Convolutional Network for Visual Question Answering.
Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence.
Heterogeneous Graph Transformer for Graph-to-Sequence Learning.
Exploring Contextual Word-level Style Relevance for Unsupervised Style Transfer.
Multi-Domain Dialogue Acts and Response Co-Generation.
Modeling Long Context for Task-Oriented Dialogue State Generation.
Meta-Reinforced Multi-Domain State Generator for Dialogue Systems.
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation.
Diversifying Dialogue Generation with Non-Conversational Text.
Out of the Echo Chamber: Detecting Countering Debate Speeches.
Exploiting Personal Characteristics of Debaters for Predicting Persuasiveness.
Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation.
tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection.
Transition-based Semantic Dependency Parsing with Pointer Networks.
Sentence Meta-Embeddings for Unsupervised Semantic Textual Similarity.
Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpus.
Controlled Crowdsourcing for High-Quality QA-SRL Annotation.
Language to Network: Conditional Parameter Adaptation with Natural Language Descriptions.
From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains.
Estimating predictive uncertainty for rumour verification models.
CorefQA: Coreference Resolution as Query-based Span Prediction.
Closing the Gap: Joint De-Identification and Concept Extraction in the Clinical Domain.
Uncertainty-Aware Curriculum Learning for Neural Machine Translation.
Gender in Danger? Evaluating Speech Translation Technology on the MuST-SHE Corpus.
Classification-Based Self-Learning for Weakly Supervised Bilingual Lexicon Induction.
Low-Dimensional Hyperbolic Knowledge Graph Embeddings.
Highway Transformer: Self-Gating Enhanced Self-Attentive Networks.
Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing.
Learning Robust Models for e-Commerce Product Search.
Document Translation vs. Query Translation for Cross-Lingual Information Retrieval in the Medical Domain.
Improving Entity Linking through Semantic Reinforced Entity Embeddings.
FLAT: Chinese NER Using Flat-Lattice Transformer.
A Two-Stage Masked LM Method for Term Set Expansion.
DRTS Parsing with Structure-Aware Encoding and Decoding.
Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing.
Semi-Supervised Semantic Dependency Parsing Using CRF Autoencoders.
Semantic Parsing for English as a Second Language.
Parsing into Variable-in-situ Logico-Semantic Graphs.
RikiNet: Reading Wikipedia Pages for Natural Question Answering.
Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehension.
R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason.
Low-Resource Generation of Multi-hop Reasoning Questions.
Harvesting and Refining Question-Answer Pairs for Unsupervised QA.
Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension.
Unsupervised Morphological Paradigm Completion.
Predicting Declension Class from Form and Meaning.
Modeling Morphological Typology for Unsupervised Learning of Language Morphology.
Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation.
Bootstrapping Techniques for Polysynthetic Morphological Analysis.
The Right Tool for the Job: Matching Model and Instance Complexities.
Learning Architectures from an Extended Search Space for Language Modeling.
Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach.
Evaluating and Enhancing the Robustness of Neural Network-based Dependency Parsing Models with Adversarial Examples.
Differentiable Window for Dynamic Local Attention.
Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification.
A Mixture of h - 1 Heads is Better than h Heads.
Words Aren't Enough, Their Order Matters: On the Robustness of Grounding Visual Referring Expressions.
Span-based Localizing Network for Natural Language Video Localization.
Knowledge Supports Visual Language Grounding: A Case Study on Colour Terms.
Cross-modal Coherence Modeling for Caption Generation.
Synchronous Double-channel Recurrent Network for Aspect-Opinion Pair Extraction.
Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language.
Representation Learning for Information Extraction from Form-like Documents.
Relation Extraction with Explanation.
Neighborhood Matching Network for Entity Alignment.
Named Entity Recognition as Dependency Parsing.
MIE: A Medical Information Extractor towards Medical Dialogues.
Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition.
Handling Rare Entities for Neural Sequence Labeling.
Continual Relation Learning via Episodic Memory Activation and Reconsolidation.
Connecting Embeddings for Knowledge Graph Entity Typing.
Bipartite Flat-Graph Network for Nested Named Entity Recognition.
Amalgamation of protein sequence, structure and textual information for improving protein-protein interaction identification.
A Top-down Neural Architecture towards Text-level Parsing of Discourse Rhetorical Structure.
Speaker Sensitive Response Evaluation Model.
SAS: Dialogue State Tracking via Slot Attention and Slot Information Sharing.
Learning Efficient Dialogue Policy from Demonstrations through Shaping.
Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog.
Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight.
A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking.
To Boldly Query What No One Has Annotated Before? The Frontiers of Corpus Querying.
The Unstoppable Rise of Computational Linguistics in Deep Learning.
The State and Fate of Linguistic Diversity and Inclusion in the NLP World.
Language (Re)modelling: Towards Embodied Language Understanding.
Are we Estimating or Guesstimating Translation Quality?
Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference.
Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization.
Leveraging Graph to Improve Abstractive Multi-Document Summarization.
Jointly Learning to Align and Summarize for Neural Cross-Lingual Summarization.
Heterogeneous Graph Neural Networks for Extractive Document Summarization.
Extractive Summarization as Text Matching.
Composing Elementary Discourse Units in Abstractive Summarization.
Automatic Generation of Citation Texts in Scholarly Papers: A Pilot Study.
Reasoning Over Semantic-Level Graph for Fact Checking.
Neural Mixed Counting Models for Dispersed Topic Discovery.
Neural Graph Matching Networks for Chinese Short Text Matching.
NeuInfer: Knowledge Inference on N-ary Facts.
How to Ask Good Questions? Try to Leverage Paraphrases.
Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder.
Do Neural Models Learn Systematicity of Monotonicity Inference in Natural Language?
Curriculum Learning for Natural Language Understanding.
Benchmarking Multimodal Regex Synthesis with Complex Structures.
Word-level Textual Adversarial Attacking as Combinatorial Optimization.
LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network.
Incorporating External Knowledge through Pre-training for Natural Language to Code Generation.
FastBERT: a Self-distilling BERT with Adaptive Inference Time.
Emerging Cross-lingual Structure in Pretrained Language Models.
Paraphrase Generation by Learning How to Edit from Samples.
Neural-DINF: A Neural Network based Framework for Measuring Document Influence.
Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation.
Tagged Back-translation Revisited: Why Does It Really Work?
Improving Neural Machine Translation with Soft Template Prediction.
Contextual Neural Machine Translation Improves Translation of Cataphoric Pronouns.
AdvAug: Robust Adversarial Augmentation for Neural Machine Translation.
Simplify the Usage of Lexicon in Chinese NER.
Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative Multiagents.
ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph Embedding.
Pyramid: A Layered Model for Nested Named Entity Recognition.
Multi-Cell Compositional LSTM for NER Domain Adaptation.
Improving Low-Resource Named Entity Recognition using Joint Sentence and Token Labeling.
Improving Event Detection via Open-domain Trigger Knowledge.
IMoJIE: Iterative Memory-Based Joint Open Information Extraction.
An Effective Transition-based Model for Discontinuous NER.
A Unified MRC Framework for Named Entity Recognition.
Video-Grounded Dialogues with Pretrained Generation Language Models.
Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks.
Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation.
Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness.
A Comprehensive Analysis of Preprocessing for Word Representation Learning in Affective Tasks.
OpinionDigest: A Simple Framework for Opinion Summarization.
Entity-Aware Dependency-Based Deep Graph Attention Network for Comparative Preference Classification.
Efficient Pairwise Annotation of Argument Quality.
Cross-Lingual Unsupervised Sentiment Classification with Multi-View Transfer Learning.
Agreement Prediction of Arguments in Cyber Argumentation for Detecting Stance Polarity and Intensity.
WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge.
STARC: Structured Annotations for Reading Comprehension.
Not All Claims are Created Equal: Choosing the Right Statistical Approach to Assess Hypotheses.
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering.
The Cascade Transformer: an Application for Efficient Answer Sentence Selection.
Selective Question Answering under Domain Shift.
SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations.
Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering.
On the Importance of Diversity in Question Generation for QA.
Logic-Guided Data Augmentation and Regularization for Consistent Question Answering.
Crossing Variational Autoencoders for Answer Retrieval.
Benefits of Intermediate Annotations in Reading Comprehension.
Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport.
Obtaining Faithful Interpretations from Compositional Neural Networks.
Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection.
Finding Universal Grammatical Relations in Multilingual BERT.
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions.
Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?
Cross-Linguistic Syntactic Evaluation of Word Prediction Models.
A Re-evaluation of Knowledge Graph Completion Methods.
Towards Debiasing Sentence Representations.
Social Biases in NLP Models as Barriers for Persons with Disabilities.
Social Bias Frames: Reasoning about Social and Power Implications of Language.
Language (Technology) is Power: A Critical Survey of "Bias" in NLP.
Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation.
Contextualizing Hate Speech Classifiers with Post-hoc Explanation.
ZPR2: Joint Zero Pronoun Recovery and Resolution using Multi-Task Learning and BERT.
PeTra: A Sparsely Supervised Memory Model for People Tracking.
Implicit Discourse Relation Classification: We Need to Talk about Evaluation.
Harnessing the linguistic signal to predict scalar inferences.
Discourse as a Function of Event: Profiling Discourse Structure in News Articles around the Main Event.
Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences.
Understanding the Language of Political Agreement and Disagreement in Legislative Texts.
Text-Based Ideal Points.
Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates.
Measuring Forecasting Skill from Text.
Hierarchical Modeling for User Personality Prediction: The Role of Message-Level Attention.
Detecting Perceived Emotions in Hurricane Disasters.
Balancing Objectives in Counseling Conversations: Advancing Forwards or Looking Backwards.
What Does BERT with Vision Look At?
Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview.
Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?
How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence.
How Can We Accelerate Progress Towards Human-like Linguistic Generalization?
Examining Citations of Natural Language Processing Literature.
Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data.
(Re)construing Meaning in NLP.
Unsupervised Opinion Summarization as Copycat-Review Generation.
The Summary Loop: Learning to Write Abstractive Summaries Without Examples.
Storytelling with Dialogue: A Critical Role Dungeons and Dragons Dataset.
Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports.
Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward.
Hooks in the Headline: Learning to Generate Headlines with Controlled Styles.
Fact-based Content Weighting for Evaluating Abstractive Summarisation.
FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization.
Exploring Content Selection in Summarization of Novel Chapters.
Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction.
Discourse-Aware Neural Extractive Text Summarization.
Asking and Answering Questions to Evaluate the Factual Consistency of Summaries.
A Transformer-based Approach for Source Code Summarization.
Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics.
S2ORC: The Semantic Scholar Open Research Corpus.
More Diverse Dialogue Datasets via Diversity-Informed Data Collection.
Facet-Aware Evaluation for Extractive Summarization.
Dialogue-Based Relation Extraction.
Code and Named Entity Recognition in StackOverflow.
Beyond Accuracy: Behavioral Testing of NLP Models with CheckList.
Adversarial NLI: A New Benchmark for Natural Language Understanding.
A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks.
Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models.
Learning Constraints for Structured Prediction Using Rectifier Networks.
Discrete Latent Variable Representations for Low-Resource Text Classification.
Shaping Visual Representations with Language for Few-Shot Classification.
Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA.
Spying on Your Neighbors: Fine-grained Probing of Contextual Embeddings for Information about Surrounding Words.
On the Spontaneous Emergence of Discrete and Compositional Signals.
Learning to Deceive with Attention-Based Explanations.
Interpreting Pretrained Contextualized Representations via Reductions to Static Embeddings.
Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models.
How does BERT's attention change when you fine-tune? An analysis methodology and a case study in negation scope.
Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training.
CraftAssist Instruction Parsing: Semantic Parsing for a Voxel-World Assistant.
Modeling Label Semantics for Predicting Emotional Reactions.
Fatality Killed the Cat or: BabelPic, a Multimodal Dataset for Non-Concrete Concepts.
ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations.
SenseBERT: Driving Some Sense into BERT.
Similarity Analysis of Contextual Word Representation Models.
On the Cross-lingual Transferability of Monolingual Representations.
Information-Theoretic Probing for Linguistic Structure.
Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words?
Toward Gender-Inclusive Coreference Resolution.
ParaCrawl: Web-Scale Acquisition of Parallel Corpora.
Dscorer: A Fast Evaluation Metric for Discourse Representation Structure Parsing.
A Corpus for Large-Scale Phonetic Typology.
Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering.
Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering.
Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings.
DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering.
Clinical Reading Comprehension: A Thorough Analysis of the emrQA Dataset.
Learning to Faithfully Rationalize by Construction.
ERASER: A Benchmark to Evaluate Rationalized NLP Models.
Compositionality and Generalization In Emergent Languages.
"Who said it, and Why?" Provenance for Natural Language Claims.
When do Word Embeddings Accurately Reflect Surveys on our Beliefs About People?
Masking Actor Information Leads to Fairer Political Claims Detection.
Analyzing Political Parody in Social Media.
Towards Emotion-aided Multi-modal Dialogue Act Classification.
Sentiment and Emotion help Sarcasm? A Multi-task Learning Framework for Multi-Modal Sarcasm, Sentiment and Emotion Analysis.
Multimodal Transformer for Multimodal Machine Translation.
Target Inference in Argument Conclusion Generation.
TaPas: Weakly Supervised Table Parsing via Pre-training.
AMR Parsing with Latent Structural Information.
Toxicity Detection: Does Context Really Matter?
Programming in Natural Language with fuSE: Synthesizing Methods from Spoken Utterances Using Deep Natural Language Understanding.
Joint Modelling of Emotion and Abusive Language Detection.
Identifying Principals and Accessories in a Complex Case based on the Comprehension of Fact Description.
Graph Neural News Recommendation with Unsupervised Preference Disentanglement.
Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction.
Empowering Active Learning to Jointly Optimize System and User Demands.
Modeling Word Formation in English-German Neural Machine Translation.
Tchebycheff Procedure for Multi-task Text Classification.
Towards Transparent and Explainable Attention Models.
Towards Faithfully Interpretable NLP Systems: How Should We Define and Evaluate Faithfulness?
Quantifying Attention Flow in Transformers.
Probing for Referential Information in Language Models.
Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT.
Make Up Your Mind! Adversarial Generation of Inconsistent Natural Language Explanations.
Analyzing analytical methods: The case of phonology in neural models of spoken language.
Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting.
Neural Reranking for Dependency Parsing: An Evaluation.
Max-Margin Incremental CCG Parsing.
Exact yet Efficient Graph Parsing, Bi-directional Locality and the Constructivist Hypothesis.
Enriched In-Order Linearization for Faster Sequence-to-Sequence Constituent Parsing.
Do Neural Language Models Show Preferences for Syntactic Formalisms?
SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis.
He said "who's gonna take care of your children when you are at ACL?": Reported Sexist Acts are Not Sexist.
GoEmotions: A Dataset of Fine-Grained Emotions.
From Arguments to Key Points: Towards Automatic Argument Summarization.
Adversarial and Domain-Aware BERT for Cross-Domain Sentiment Analysis.
CluBERT: A Cluster-Based Approach for Learning Sense Distributions in Multiple Languages.
BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance.
Autoencoding Pixies: Amortised Variational Inference with Graph Convolutions for Functional Distributional Semantics.
Autoencoding Keyword Correlation Graph for Document Clustering.
Analysing Lexical Semantic Change with Contextualised Word Representations.
Adaptive Compression of Word Embeddings.
An Effectiveness Metric for Ordinal Classification: Formal Properties and Experimental Results.
Graph-to-Tree Learning for Solving Math Word Problems.
A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction.
Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture.
Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation.
SEEK: Segmented Embedding of Knowledge Graphs.
Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning.
Bayesian Hierarchical Words Representation Learning.
Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data.
Learning Implicit Text Generation via Feature Matching.
It Takes Two to Lie: One to Lie, and One to Listen.
Neural Temporal Opinion Modelling for Opinion Prediction on Twitter.
Towards end-2-end learning for predicting behavior codes from spoken utterances in psychotherapy conversations.
SimulSpeech: End-to-End Simultaneous Speech to Text Translation.
Reasoning with Multimodal Sarcastic Tweets via Modeling Cross-Modality Contrast and Semantic Association.
Meta-Transfer Learning for Code-Switched Speech Recognition.
Learning Spoken Language Representations with Neural Lattice Language Modeling.
Improving Disfluency Detection by Self-Training a Self-Attentive Model.
How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems.
Curriculum Pre-training for End-to-End Speech Translation.
CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotation of Modality.
Transition-based Directed Graph Construction for Emotion-Cause Pair Extraction.
SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics.
Relation-Aware Collaborative Learning for Unified Aspect-Based Sentiment Analysis.
Don't Eclipse Your Arts Due to Small Discrepancies: Boundary Repositioning with a Pointer Network for Aspect Extraction.
Aspect Sentiment Classification with Document-level Sentiment Preference Modeling.
Investigating Word-Class Distributions in Word Vector Spaces.
Hypernymy Detection for Low-Resource Languages via Meta Learning.
Biomedical Entity Representations with Synonym Marginalization.
BiRRE: Learning Bidirectional Residual Relation Embeddings for Supervised Hypernymy Detection.
Towards Holistic and Automatic Evaluation of Open-Domain Dialogue Generation.
That is a Known Lie: Detecting Previously Fact-Checked Claims.
MIND: A Large-scale Dataset for News Recommendation.
MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization.
GLUECoS: An Evaluation Benchmark for Code-Switched NLP.
ChartDialogs: Plotting from Natural Language Instructions.
Automatic Machine Translation Evaluation using Source Language Inputs and Cross-lingual Language Model.
On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation.
Lexically Constrained Neural Machine Translation with Levenshtein Transformer.
Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation.
Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change.
Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation.
A Simple and Effective Unified Encoder for Document-Level Machine Translation.
A Retrieve-and-Rewrite Initialization Method for Unsupervised Machine Translation.
A Reinforced Generation of Adversarial Examples for Neural Machine Translation.
A Graph-based Coarse-to-fine Method for Unsupervised Bilingual Lexicon Induction.
SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions.
On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond.
Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention.
Do you have the right scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods.
A Relational Memory-based Embedding Model for Triple Classification and Search Personalization.
Understanding Attention for Text Classification.
Roles and Utilization of Attention Heads in Transformer-based Neural Language Models.
On the Robustness of Language Encoders against Grammatical Errors.
An Analysis of the Utility of Explicit Negative Examples to Improve the Syntactic Abilities of Neural Language Models.
What Was Written vs. Who Read It: News Media Profiling Using Text Analysis and Social Media Context.
Stock Embeddings Acquired from News Articles and Price History, and an Application to Portfolio Optimization.
Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer.
Dynamic Online Conversation Recommendation.
Structure-Level Knowledge Distillation For Multilingual Sequence Labeling.
Representations of Syntax [MASK] Useful: Effects of Constituency and Dependency Structure in Recursive LSTMs.
Efficient Second-Order TreeCRF for Neural Dependency Parsing.
Efficient Constituency Parsing by Pointing.
An Empirical Comparison of Unsupervised Constituency Parsing Methods.
A Span-based Linearization for Constituent Trees.
Towards Better Non-Tree Argument Mining: Proposition-Level Biaffine Parsing with Task-Specific Parameterization.
Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks.
SpanMlt: A Span-based Multi-Task Learning Framework for Pair-wise Aspect and Opinion Terms Extraction.
Relational Graph Attention Network for Aspect-based Sentiment Analysis.
Parallel Data Augmentation for Formality Style Transfer.
Modelling Context and Syntactical Features for Aspect-based Sentiment Analysis.
KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis.
Enhancing Cross-target Stance Detection with Transferable Semantic-Emotion Knowledge.
Embarrassingly Simple Unsupervised Aspect Extraction.
Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair Extraction.
ECPE-2D: Emotion-Cause Pair Extraction based on Joint Two-Dimensional Representation, Interaction and Prediction.
Analyzing the Persuasive Effect of Style in News Editorial Argumentation.
Towards Interpretable Clinical Diagnosis with Bayesian Network Ensembles Stacked on Entity-Aware CNNs.
MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs.
Improving Segmentation for Technical Support Problems.
Hyperbolic Capsule Networks for Multi-Label Classification.
HyperCore: Hyperbolic and Co-graph Representation for Automatic ICD Coding.
Hiring Now: A Skill-Aware Multi-Attention Model for Job Posting Generation.
Distinguish Confusing Law Articles for Legal Judgment Prediction.
Camouflaged Chinese Spam Content Detection with Semi-supervised Generative Active Learning.
On the Inference Calibration of Neural Machine Translation.
Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation.
Geometry-aware domain adaptation for unsupervised alignment of word embeddings.
Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation.
A Relaxed Matching Procedure for Unsupervised BLI.
A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation.
Zero-shot Text Classification via Reinforced Self-training.
Single Model Ensemble using Pseudo-Tags and Distinct Vectors.
Improving Transformer Models by Reordering their Sublayers.
How Does Selective Mechanism Improve Self-Attention Networks?
Estimating the influence of auxiliary tasks for multi-task learning of sequence tagging tasks.
Attentive Pooling with Learnable Norms for Text Representation.
A Probabilistic Generative Model for Typographical Analysis of Early Modern Printing.
Towards Understanding Gender Bias in Relation Extraction.
Mitigating Gender Bias Amplification in Distribution by Posterior Regularization.
It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations.
Is Your Classifier Actually Biased? Measuring Fairness under Uncertainty with Bernstein Bounds.
Give Me Convenience and Give Her Death: Who Should Decide What Uses of NLP are Appropriate, and on What Basis?
Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer.
Verbal Multiword Expressions for Identification of Metaphor.
Predicting Degrees of Technicality in Automatic Terminology Extraction.
Multidirectional Associative Optimization of Function-Specific Word Representations.
Glyph2Vec: Learning Chinese Out-of-Vocabulary Word Embedding from Glyphs.
Breaking Through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information.
Simultaneous Translation Policies: From Fixed to Adaptive.
On The Evaluation of Machine Translation SystemsTrained With Back-Translation.
Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation.
ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation.
schuBERT: Optimizing Elements of BERT.
Weight Poisoning Attacks on Pretrained Models.
Topological Sort for Sentence Ordering.
Span Selection Pre-training for Question Answering.
Showing Your Work Doesn't Always Work.
Robust Encodings: A Framework for Combating Adversarial Typos.
Pretrained Transformers Improve Out-of-Distribution Robustness.
Posterior Control of Blackbox Generation.
Posterior Calibrated Training on Sentence Classification Tasks.
Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding.
Masked Language Model Scoring.
Low Resource Sequence Tagging using Sentence Reconstruction.
Knowledge Graph Embedding Compression.
Interactive Classification by Asking Informative Questions.
Contextual Embeddings: When Are They Worth It?
A Batch Normalized Inference Network Keeps the KL Vanishing Away.
What is Learned in Visually Grounded Neural Syntax Acquisition.
MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning.
Learning to execute instructions in a Minecraft dialogue.
Learning to Segment Actions from Observation and Narration.
Cross-media Structured Common Space for Multimedia Event Extraction.
BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps.
Simple and Effective Retrieve-Edit-Rerank Text Generation.
Improving Adversarial Text Generation by Modeling the Distant Future.
INSET: Sentence Infilling with INter-SEntential Transformer.
Enabling Language Models to Fill in the Blanks.
Bridging the Structural Gap Between Encoding and Decoding for Data-To-Text Generation.
Automatic Poetry Generation from Prosaic Text.
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents.
Neural Generation of Dialogue Response Timings.
Learning an Unreferenced Metric for Online Dialogue Evaluation.
Image-Chat: Engaging Grounded Conversations.
Grounding Conversations with Improvised Dialogues.
Phone Features Improve Speech Translation.
Multimodal and Multiresolution Speech Recognition with Transformers.
MultiQT: Multimodal learning for real-time question tracking in speech.
Integrating Multimodal Information in Large Pretrained Transformers.
Improved Speech Representations with Multi-Target Autoregressive Predictive Coding.
Syntactic Data Augmentation Increases Robustness to Inference Heuristics.
Interactive Machine Comprehension with Information Seeking Agents.
INFOTABS: Inference on Tables as Semi-structured Data.
Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction.
Semantic Scaffolds for Pseudocode-to-Code Generation.
SPECTER: Document-level Representation Learning using Citation-informed Transformers.
Investigating the effect of auxiliary objectives for the automated grading of learner English speech transcriptions.
Efficient Strategies for Hierarchical Text Classification: External Knowledge and Auxiliary Tasks.
DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference.
A Girl Has A Name: Detecting Authorship Obfuscation.
XtremeDistil: Multi-stage Distillation for Massive Multilingual Models.
Why Overfitting Isn't Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries.
To Pretrain or Not to Pretrain: Examining the Benefits of Pretrainng on Resource Rich Tasks.
Taxonomy Construction of Unseen Domains via Graph-based Cross-Domain Knowledge Transfer.
Stolen Probability: A Structural Weakness of Neural Language Models.
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization.
On Importance Sampling-Based Evaluation of Latent Language Models.
MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices.
MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification.
Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling.
Generalizing Natural Language Analysis through Span-relation Representations.
GAN-BERT: Generative Adversarial Learning for Robust Text Classification with a Bunch of Labeled Examples.
ExpBERT: Representation Engineering with Natural Language Explanations.
Active Imitation Learning with Noisy Guidance.
Calibrating Structured Output Predictors for Natural Language Processing.
Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback.
Recursive Template-based Frame Generation for Task Oriented Dialog.
Negative Training for Neural Dialogue Response Generation.
Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs.
Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills.
"None of the Above": Measure Uncertainty in Dialog Response Retrieval.
What determines the order of adjectives in English? Comparing efficiency-based theories using dependency treebanks.
Speakers enhance contextually confusable words.
Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment.
Recollection versus Imagination: Exploring Human Memory and Cognition via Neural Language Models.
Probing Linguistic Systematicity.
A Tale of Two Perplexities: Sensitivity of Neural Language Models to Lexical Retrieval Deficits in Dementia of the Alzheimer's Type.
Unsupervised Opinion Summarization with Noising and Denoising.
Screenplay Summarization Using Latent Narrative Structure.
On Faithfulness and Factuality in Abstractive Summarization.
Attend to Medical Ontologies: Content Selection for Clinical Abstractive Summarization.
Improving Non-autoregressive Neural Machine Translation with Monolingual Data.
BPE-Dropout: Simple and Effective Subword Regularization.
Politeness Transfer: A Tag and Generate Approach.
Learning to Update Natural Language Comments Based on Code Changes.
GPT-too: A Language-Model-First Approach for AMR-to-Text Generation.
Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation.
Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing.
Automatic Detection of Generated Text is Easiest when Humans are Fooled.
A Generative Model for Joint Natural Language Understanding and Generation.
You Don't Have Time to Read This: An Exploration of Document Reading Time Prediction.
Suspense in Short Stories is Predicted By Uncertainty Reduction over Neural Story Representation.
Overestimation of Syntactic Representation in Neural Language Models.
Inflecting When There's No Majority: Limitations of Encoder-Decoder Neural Networks as Cognitive Models for German Plurals.
A Systematic Assessment of Syntactic Generalization in Neural Language Models.
Will-They-Won't-They: A Very Large Dataset for Stance Detection on Twitter.
A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages.
MMPE: A Multi-Modal Interface for Post-Editing Machine Translation.
"You Sound Just Like Your Father" Commercial Machine Translation Systems Include Stylistic Biases.
Self-Attention with Cross-Lingual Position Representation.
Parallel Sentence Mining by Constrained Decoding.
On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation.
Language-aware Interlingua for Multilingual Neural Machine Translation.
It's Easier to Translate out of English than into it: Measuring Neural Translation Difficulty by Cross-Mutual Information.
Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation.
Enhancing Machine Translation with Dependency-Aware Self-Attention.
End-to-End Neural Word Alignment Outperforms GIZA++.
Character-Level Translation with Self-attention.
Boosting Neural Machine Translation with Similar Translations.
Bilingual Dictionary Based Neural Machine Translation without Using Parallel Sentences.
TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task.
Reasoning with Latent Structure Refinement for Document-Level Relation Extraction.
Probing Linguistic Features of Sentence-Level Representations in Relation Extraction.
Named Entity Recognition without Labelled Data: A Weak Supervision Approach.
NAT: Noise-Aware Training for Robust Neural Sequence Labeling.
In Layman's Terms: Semi-Open Relation Extraction from Scientific Texts.
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction.
Semantic Graphs for Generating Deep Questions.
Fast and Accurate Non-Projective Dependency Tree Linearization.
Dialogue Coherence Assessment Without Explicit Dialogue Act Labels.
Bridging Anaphora Resolution as Question Answering.
You Impress Me: Dialogue Generation via Mutual Persona Perception.
MuTual: A Dataset for Multi-Turn Dialogue Reasoning.
Learning Dialog Policies from Weak Demonstrations.
Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network.
Conversational Word Embedding for Retrieval-Based Dialog System.
Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation.
Self-Attention Guided Copy Mechanism for Abstractive Summarization.
SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization.
Improving Truthfulness of Headline Generation.
Examining the State-of-the-Art in News Timeline Summarization.
Attend, Translate and Summarize: An Efficient Method for Neural Cross-Lingual Summarization.
A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal.
AMR Parsing via Graph-Sequence Iterative Inference.
iSarcasm: A Dataset of Intended Sarcasm.
The TechQA Dataset.
The SOFC-Exp Corpus and Neural Approaches to Information Extraction in the Materials Science Domain.
PuzzLing Machines: A Challenge on Learning From Small Data.
Multimodal Quality Estimation for Machine Translation.
Multi-Hypothesis Machine Translation Evaluation.
Learning and Evaluating Emotion Lexicons for 91 Languages.
KLEJ: Comprehensive Benchmark for Polish Language Understanding.
Generating Counter Narratives against Online Hate Speech: Data and Strategies.
Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences.
Crawling and Preprocessing Mailing Lists At Scale for Dialog Analysis.
Building a User-Generated Content North-African Arabizi Treebank: Tackling Hell.
A Graph Auto-encoder Model of Derivational Morphology.
Keyphrase Generation for Scientific Document Retrieval.
Hierarchy-Aware Global Model for Hierarchical Text Classification.
Exclusive Hierarchical Decoding for Deep Keyphrase Generation.
Dynamic Memory Induction Networks for Few-Shot Text Classification.
Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints.
Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen.
Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification.
Towards Conversational Recommendation over Multi-Type Dialogs.
DTCA: Decision Tree-based Co-Attention Networks for Explainable Claim Verification.
Code-Switching Patterns Can Be an Effective Route to Improve Performance of Downstream NLP Applications: A Case Study of Humour, Sarcasm and Hate Speech Detection.
Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders.
Revisiting the Context Window for Cross-lingual Word Embeddings.
Improving Image Captioning Evaluation by Considering Inter References Variance.
A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers.
Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases.
Learning to Identify Follow-Up Questions in Conversational Question Answering.
Injecting Numerical Reasoning Skills into Language Models.
Explicit Memory Tracker with Coarse-to-Fine Reasoning for Conversational Machine Reading.
Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension.
Dynamic Sampling Strategies for Multi-Task Reading Comprehension.
Contextualized Sparse Representations for Real-Time Open-Domain Question Answering.
A Methodology for Creating Question Answering Corpora Using Inverse Data Annotation.
A Frame-based Sentence Representation for Machine Reading Comprehension.
Spelling Error Correction with Soft-Masked BERT.
SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check.
Modeling Code-Switch Languages Using Bilingual Parallel Corpus.
Interpreting Twitter User Geolocation.
Interpretable Operational Risk Classification with Semi-Supervised Variational Autoencoder.
Fine-grained Interest Matching for Neural News Recommendation.
Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning.
"The Boating Store Had Its Best Sail Ever": Pronunciation-attentive Contextualized Pun Recognition.
Unsupervised FAQ Retrieval with Question Generation and BERT.
Tree-Structured Neural Topic Model.
Interactive Construction of User-Centric Dictionary for Text Analytics.
Generative Semantic Hashing Enhanced via Boltzmann Machines.
An Online Semantic-enhanced Dirichlet Model for Short Text Stream Clustering.
Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation.
Rigid Formats Controlled Text Generation.
Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention Networks.
Improved Natural Language Generation via Loss Truncation.
Explicit Semantic Decomposition for Definition Generation.
USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation.
Towards Unsupervised Language Understanding and Generation by Joint Dual Learning.
Semi-Supervised Dialogue Policy Learning via Stochastic Reward Estimation.
Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation.
Paraphrase Augmented Task-Oriented Dialog Generation.
Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition.
Learning to Tag OOV Tokens by Integrating Contextual Representation and Background Knowledge.
Learning Low-Resource End-To-End Goal-Oriented Dialog for Fast and Reliable System Deployment.
Gated Convolutional Bidirectional Attention-based Model for Off-topic Spoken Response Detection.
Evaluating Dialogue Generation Systems via Response Selection.
End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2.
Efficient Dialogue State Tracking by Selectively Overwriting Memory.
CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation.
Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora.
Predicting the Topical Stance and Political Leaning of Media using Tweets.
Integrating Semantic and Structural Information with Graph Convolutional Network for Controversy Detection.
GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media.
Language Models as an Alternative Evaluator of Word Order Hypotheses: A Case Study in Japanese.
Emergence of Syntax Needs Minimal Supervision.
Dice Loss for Data-imbalanced NLP Tasks.
A Three-Parameter Rank-Frequency Relation in Natural Languages.
A Formal Hierarchy of RNN Architectures.
Opportunistic Decoding with Timely Correction for Simultaneous Translation.
Norm-Based Curriculum Learning for Neural Machine Translation.
Multiscale Collaborative Deep Models for Neural Machine Translation.
Location Attention for Extrapolation to Longer Sequences.
Lipschitz Constrained Parameter Initialization for Deep Transformers.
Learning Source Phrase Representations for Neural Machine Translation.
Jointly Masked Sequence-to-Sequence Model for Non-Autoregressive Neural Machine Translation.
Evaluating Explanation Methods for Neural Machine Translation.
Content Word Aware Neural Machine Translation.
Text Classification with Negative Supervision.
Neural Topic Modeling with Bidirectional Adversarial Training.
Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks.
Contextualized Weak Supervision for Text Classification.
A Joint Model for Document Segmentation and Segment Labeling.
Unsupervised Paraphrasing by Simulated Annealing.
TAG : Type Auxiliary Guiding for Code Comment Generation.
Review-based Question Generation with Adaptive Instance Transfer and Augmentation.
Reverse Engineering Configurations of Neural Text Generation Models.
Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order.
Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders.
Neural Syntactic Preordering for Controlled Paraphrase Generation.
Learning to Ask More: Semi-Autoregressive Sequential Question Generation under Dual-Graph Interaction.
Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs.
Fluent Response Generation for Conversational Question Answering.
Few-Shot NLG with Pre-Trained Language Model.
Fact-based Text Editing.
Cross-modal Language Generation using Pivot Stabilization for Web-scale Language Coverage.
A Study of Non-autoregressive Model for Sequence Generation.
TransS-Driven Joint Learning Architecture for Implicit Discourse Relation Recognition.
A Complete Shift-Reduce Chinese Discourse Parser with Robust Dynamic Oracle.
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking.
Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations.
Slot-consistent NLG for Task-oriented Dialogue Systems with Iterative Rectification Network.
PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable.
Large Scale Multi-Actor Generative Dialog Modeling.
Guiding Variational Response Generator to Exploit Persona.
Generating Informative Conversational Response using Recurrent Knowledge-Interaction and Knowledge-Copy.
Dialogue State Tracking with Explicit Slot Connection Modeling.
Designing Precise and Robust Dialogue Response Evaluators.
Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling.
Predicting Depression in Screening Interviews from Latent Categorization of Interview Prompts.
Learning to Understand Child-directed and Adult-directed Speech.
