acl 2019 论文列表
Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers.
|
Learning to Relate from Captions and Bounding Boxes.
Multimodal Abstractive Summarization for How2 Videos.
Visual Story Post-Editing.
Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-ray Reports.
Multimodal Transformer for Unaligned Multimodal Language Sequences.
Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation.
VIFIDEL: Evaluating the Visual Fidelity of Image Descriptions.
Distilling Translations with Visual Awareness.
Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning.
CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication.
Informative Image Captioning with External Sources of Information.
Lattice Transformer for Speech Translation.
Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog.
Symbolic Inductive Bias for Visually Grounded Learning of Spoken Language.
What Should I Ask? Using Conversationally Informative Rewards for Goal-oriented Visual Dialog.
Learning to Discover, Ground and Use Words with Segmental Neural Language Models.
A Corpus for Reasoning about Natural Language Grounded in Photographs.
Identifying Visible Actions in Lifestyle Vlogs.
Latent Variable Model for Multi-modal Translation.
Dense Procedure Captioning in Narrated Instructional Videos.
Topic Modeling with Wasserstein Autoencoders.
A Multi-Task Architecture on Relevance-based Neural Query Translation.
Encouraging Paragraph Embeddings to Remember Sentence Identity Improves Classification.
Why Didn't You Listen to Me? Comparing User Control of Human-in-the-Loop Topic Models.
Large-Scale Multi-Label Text Classification on EU Legislation.
Numeracy-600K: Learning Numeracy for Detecting Exaggerated Information in Market Comments.
Bias Analysis and Mitigation in the Evaluation of Authorship Verification.
Hierarchical Transfer Learning for Multi-label Text Classification.
Matching Article Pairs with Graphical Decomposition and Convolutions.
Incorporating Priors with Feature Attribution on Text Classification.
Inducing Document Structure for Aspect-based Summarization.
Discourse Representation Parsing for Sentences and Documents.
Sentence Centrality Revisited for Unsupervised Summarization.
An Automated Framework for Fast Cognate Detection and Bayesian Phylogenetic Inference in Computational Historical Linguistics.
Accelerating Sparse Matrix Operations in Neural Networks on Graphics Processing Units.
Wetin dey with these comments? Modeling Sociolinguistic Factors Affecting Code-switching Behavior in Nigerian Online Discussions.
Exploiting Sentential Context for Neural Machine Translation.
Reducing Word Omission Errors in Neural Machine Translation: A Contrastive Learning Approach.
MC\^2: Multi-perspective Convolutional Cube for Conversational Machine Reading Comprehension.
Are Red Roses Red? Evaluating Consistency of Question-Answering Models.
Synthetic QA Corpora Generation with Roundtrip Consistency.
Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions.
NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language.
Dynamically Fused Graph Network for Multi-hop Reasoning.
Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering.
Careful Selection of Knowledge to Solve Open Book Question Answering.
Combining Knowledge Hunting and Neural Language Models to Solve the Winograd Schema Challenge.
Multi-hop Reading Comprehension through Question Decomposition and Rescoring.
Latent Retrieval for Weakly Supervised Open Domain Question Answering.
RankQA: Neural Question Answering with Answer Re-Ranking.
Improving the Robustness of Question Answering Systems to Question Paraphrasing.
Automatic Grammatical Error Correction for Sequence-to-sequence Text Generation: An Empirical Study.
Large-Scale Transfer Learning for Natural Language Generation.
Negative Lexically Constrained Decoding for Paraphrase Generation.
Storyboarding of Recipes: Grounded Contextual Generation.
Unsupervised Paraphrasing without Translation.
Self-Attention Architectures for Answer-Agnostic Neural Question Generation.
Learning to Control the Fine-grained Sentiment for Story Ending Generation.
Generating Sentences from Disentangled Syntactic and Semantic Spaces.
Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation.
Towards Comprehensive Description Generation from Factual Attribute-value Tables.
Controllable Paraphrase Generation with a Syntactic Exemplar.
Barack's Wife Hillary: Using Knowledge Graphs for Fact-Aware Language Modeling.
Automated Chess Commentator Powered by Neural Chess Engine.
Curate and Generate: A Corpus and Method for Joint Control of Semantics and Style in Neural NLG.
BAM! Born-Again Multi-Task Networks for Natural Language Understanding.
Interpolated Spectral NGram Language Models.
The Referential Reader: A Recurrent Entity Network for Anaphora Resolution.
Optimal Transport-based Alignment of Learned Character Representations for String Similarity.
Task Refinement Learning for Improved Accuracy and Stability of Unsupervised Domain Adaptation.
Variational Pretraining for Semi-supervised Text Classification.
Model-Agnostic Meta-Learning for Relation Classification with Limited Supervision.
Using Human Attention to Extract Keyphrase from Microblog Post.
A Semi-Markov Structured Support Vector Machine Model for High-Precision Named Entity Recognition.
Low-resource Deep Entity Resolution with Transfer and Active Learning.
Merge and Label: A Novel Neural Network Architecture for Nested NER.
Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records.
Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation.
Simultaneous Translation with Flexible Policy via Restricted Imitation Learning.
Better OOV Translation with Bilingual Terminology Mining.
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned.
Generalized Data Augmentation for Low-Resource Translation.
Confusionset-guided Pointer Networks for Chinese Spelling Check.
Corpus-based Check-up for Thesaurus.
Collocation Classification with Unsupervised Relation Vectors.
Deep Neural Model Inspection and Comparison via Functional Neuron Pathways.
Probing for Semantic Classes: Diagnosing the Meaning Content of Word Embeddings.
Empirical Linguistic Study of Sentence Embeddings.
Predicting Humorousness and Metaphor Novelty with Gaussian Process Preference Learning.
Modeling Semantic Compositionality with Sememe Knowledge.
Word2Sense: Sparse Interpretable Word Embeddings.
Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation.
Zero-shot Word Sense Disambiguation using Sense Definition Embeddings.
Improving Neural Conversational Models with Entropy-Based Data Filtering.
Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good.
Target-Guided Open-Domain Conversation.
Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems.
Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes.
An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing.
Combating Adversarial Misspellings with Robust Word Recognition.
Towards Explainable NLP: A Generative Explanation Framework for Text Classification.
Generating Fluent Adversarial Examples for Natural Languages.
Depth Growing for Neural Machine Translation.
Towards Integration of Statistical Hypothesis Tests into Deep Neural Networks.
Reversing Gradients in Adversarial Domain Adaptation for Question Deduplication and Textual Entailment Tasks.
Soft Contextual Data Augmentation for Neural Machine Translation.
Misleading Failures of Partial-input Baselines.
Better Exploiting Latent Variables in Text Modeling.
Neural-based Chinese Idiom Recommendation for Enhancing Elegance in Essay Writing.
Learning Latent Trees with Stochastic Perturbations and Differentiable Dynamic Programming.
Rationally Reappraising ATIS-based Dialogue Systems.
Modeling Semantic Relationship in Multi-turn Conversations with Hierarchical Latent Variables.
Deep Unknown Intent Detection with Margin Loss.
Robust Zero-Shot Cross-Domain Slot Filling with Example Values.
SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking.
Dual Supervised Learning for Natural Language Understanding and Generation.
A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling.
Reading Turn by Turn: Hierarchical Attention Architecture for Spoken Dialogue Comprehension.
Personalizing Dialogue Agents via Meta-Learning.
Memory Consolidation for Contextual Spoken Language Understanding with Dialogue Logistic Inference.
Ordinal and Attribute Aware Response Generation in a Multimodal Dialogue System.
Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading.
Neural Response Generation with Meta-words.
Collaborative Dialogue in Minecraft.
Training Neural Response Selection for Task-Oriented Dialogue Systems.
Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment.
Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset.
Label-Agnostic Sequence Labeling by Copying Nearest Neighbors.
A Prism Module for Semantic Disentanglement in Name Entity Recognition.
Sequence Labeling Parsing by Learning across Representations.
PTB Graph Parsing with Tree Approximation.
How to Best Use Syntax in Semantic Role Labelling.
Online Infix Probability Computation for Probabilistic Finite Automata.
Neural Architectures for Nested NER through Linearization.
Enhancing Unsupervised Generative Dependency Parser with Contextual Information.
Span-Level Model for Relation Extraction.
Towards Improving Neural Named Entity Recognition with Gazetteers.
Improving Open Information Extraction via Iterative Rank-Aware Learning.
Exploring Pre-trained Language Models for Event Extraction and Generation.
Cost-sensitive Regularization for Label Confusion-aware Event Detection.
Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision.
Joint Slot Filling and Intent Detection via Capsule Neural Networks.
A Deep Reinforced Sequence-to-Set Model for Multi-Label Classification.
Quantity Tagger: A Latent-Variable Sequence Labeling Approach to Solving Addition-Subtraction Word Problems.
A Unified Multi-task Adversarial Learning Framework for Pharmacovigilance Mining.
Incorporating Linguistic Constraints into Keyphrase Generation.
Scaling up Open Tagging from Tens to Thousands: Comprehension Empowered Attribute Value Extraction from Product Title.
Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Construction.
Improving Textual Network Embedding with Global Attention via Optimal Transport.
Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks.
NNE: A Dataset for Nested Named Entity Recognition in English Newswire.
Word-order Biases in Deep-agent Emergent Communication.
Modeling Affirmative and Negated Action Processing in the Brain with Lexical and Compositional Semantic Models.
Relating Simple Sentence Representations in Deep Neural Networks and the Brain.
Like a Baby: Visually Situated Neural Language Acquisition.
Morphological Irregularity Correlates with Frequency.
Generating Summaries with Topic Templates and Structured Convolutional Decoders.
Simple Unsupervised Summarization by Contextual Matching.
Studying Summarization Evaluation Metrics in the Appropriate Scoring Range.
Abstractive Text Summarization Based on Deep Learning and Semantic Content Generalization.
Hierarchical Transformers for Multi-Document Summarization.
HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization.
Tree LSTMs with Convolution Units to Predict Stance and Rumor Veracity in Social Media Conversations.
Asking the Crowd: Question Analysis, Evaluation and Generation for Open Discussion on Online Forums.
TWEETQA: A Social Media Focused Question Answering Dataset.
Automatically Identifying Complaints in Social Media.
Bilingual Lexicon Induction through Unsupervised Machine Translation.
How Multilingual is Multilingual BERT?
Analyzing the Limitations of Cross-lingual Word Embedding Mappings.
What Kind of Language Is Hard to Language-Model?
Multilingual and Cross-Lingual Graded Lexical Entailment.
A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings Based on Graph Modularity.
Interpretable Question Answering on Knowledge Bases and Text.
Explain Yourself! Leveraging Language Models for Commonsense Reasoning.
Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives.
MultiQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension.
Unsupervised Question Answering by Cloze Translation.
Handling Divergent Reference Texts when Evaluating Table-to-Text Generation.
A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer.
Cross-Lingual Training for Automatic Question Generation.
Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling.
Coherent Comments Generation for Chinese Articles with a Graph-to-Sequence Model.
A Surprisingly Robust Trick for the Winograd Schema Challenge.
Attention Is (not) All You Need for Commonsense Reasoning.
Generalized Tuning of Distributional Word Vectors for Monolingual and Cross-Lingual Lexical Entailment.
Learning to Rank for Plausible Plausibility.
Every Child Should Have Parents: A Taxonomy Refinement Algorithm Based on Hyperbolic Term Embeddings.
Unified Semantic Parsing with Weak Supervision.
HellaSwag: Can a Machine Really Finish Your Sentence?
Detecting Subevents using Discourse and Narrative Features.
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction.
A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching.
Duality of Link Prediction and Entailment Graph Induction.
Neural Network Alignment for Sentential Paraphrases.
Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs.
Simple and Effective Text Matching with Richer Alignment Features.
An Empirical Study of Span Representations in Argumentation Structure Parsing.
Yes, we can! Mining Arguments in 50 Years of US Presidential Campaign Debates.
Context-aware Embedding for Targeted Aspect-based Sentiment Analysis.
Toward Comprehensive Understanding of a Sentiment Based on Human Motives.
Recognising Agreement and Disagreement between Stances with Reason Comparing Networks.
Probing Neural Network Comprehension of Natural Language Arguments.
An Investigation of Transfer Learning-Based Sentiment Analysis in Japanese.
Latent Variable Sentiment Grammar.
Determining Relative Argument Specificity and Stance for Complex Argumentative Structures.
Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper).
Second-Order Semantic Dependency Parsing with End-to-End Neural Networks.
Simple and Effective Paraphrastic Similarity from Parallel Translations.
BERT Rediscovers the Classical NLP Pipeline.
Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning.
Compositional Semantic Parsing across Graphbanks.
Human vs. Muppet: A Conservative Estimate of Human Performance on the GLUE Benchmark.
Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing.
Reranking for Neural Semantic Parsing.
SemBleu: A Robust Metric for AMR Parsing Evaluation.
EigenSent: Spectral sentence embeddings using higher-order Dynamic Mode Decomposition.
Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation.
SParC: Cross-Domain Semantic Parsing in Context.
DisSent: Learning Sentence Representations from Explicit Discourse Relations.
Multi-Task Deep Neural Networks for Natural Language Understanding.
Complex Question Decomposition for Semantic Parsing.
Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling.
Zero-Shot Semantic Parsing for Instructions.
Language Modeling with Shared Grammar.
Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index.
Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets.
Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data.
Embedding Time Expressions for Deep Temporal Ordering Models.
Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures.
A2N: Attending to Neighbors for Knowledge Graph Inference.
Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge.
Distilling Discrimination and Generalization Knowledge for Event Detection via Delta-Representation Learning.
AutoML Strategy Based on Grammatical Evolution: A Case Study about Knowledge Discovery from Text.
Beyond BLEU: Training Neural Machine Translation with Semantic Similarity.
Bridging the Gap between Training and Inference for Neural Machine Translation.
Robust Neural Machine Translation with Doubly Adversarial Inputs.
Neural Legal Judgment Prediction in English.
Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network.
Towards Near-imperceptible Steganographic Text.
Course Concept Expansion in MOOCs with External Knowledge and Interactive Game.
Eliciting Knowledge from Experts: Automatic Transcript Parsing for Cognitive Task Analysis.
The Language of Legal and Illegal Activity on the Darknet.
AdaNSP: Uncertainty-driven Adaptive Decoding in Neural Semantic Parsing.
Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader.
Compositional Questions Do Not Necessitate Multi-hop Reasoning.
Learning to Ask Unanswerable Questions for Machine Reading Comprehension.
Open-Domain Why-Question Answering with Adversarial Learning to Encode Answer Texts.
Multi-Relational Script Learning for Discourse Relations.
Do You Know That Florence Is Packed with Visitors? Evaluating State-of-the-art Models of Speaker Commitment.
Employing the Correspondence of Relations and Connectives to Identify Implicit Discourse Relations via Label Embeddings.
A Unified Linear-Time Framework for Sentence-Level Discourse Parsing.
Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution.
Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection.
Keeping Notes: Conditional Natural Language Generation with a Scratchpad Encoder.
TIGS: An Inference Algorithm for Text Infilling with Gradient Search.
Bayes Test of Precision, Recall, and F1 Measure for Comparison of Two Natural Language Processing Models.
Learning Transferable Feature Representations Using Neural Networks.
Neural Temporality Adaptation for Document Classification: Diachronic Word Embeddings and Domain Adaptation Models.
Few-Shot Representation Learning for Out-Of-Vocabulary Words.
Learning How to Active Learn by Dreaming.
Distant Learning for Entity Linking with Automatic Noise Detection.
Hubless Nearest Neighbor Search for Bilingual Lexicon Induction.
Self-Attentive, Multi-Context One-Class Classification for Unsupervised Anomaly Detection on Text.
Exploiting Invertible Decoders for Unsupervised Sentence Representation Learning.
Leveraging Meta Information in Short Text Aggregation.
Towards Language Agnostic Universal Representations.
Large Dataset and Language Model Fun-Tuning for Humor Recognition.
Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation.
Pay Attention when you Pay the Bills. A Multilingual Corpus with Dependency-based and Semantic Annotation of Collocations.
Crowdsourcing and Validating Event-focused Emotion Corpora for German and English.
Give Me More Feedback II: Annotating Thesis Strength and Related Attributes in Student Essays.
Fine-Grained Sentence Functions for Short-Text Conversation.
How Large Are Lions? Inducing Distributions over Quantitative Attributes.
StRE: Self Attentive Edit Quality Prediction in Wikipedia.
The KnowRef Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution.
Attention-based Conditioning Methods for External Knowledge Integration.
On the Distribution of Deep Clausal Embeddings: A Large Cross-linguistic Study.
Is Word Segmentation Child's Play in All Languages?
Uncovering Probabilistic Implications in Typological Knowledge Bases.
CNNs found to jump around more skillfully than RNNs: Compositional Generalization in Seq2seq Convolutional Networks.
Miss Tools and Mr Fruit: Emergent Communication in Agents Learning about Object Affordances.
Diachronic Sense Modeling with Deep Contextualized Word Embeddings: An Ecological View.
End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories.
A Spreading Activation Framework for Tracking Conceptual Complexity of Texts.
Are we there yet? Encoder-decoder neural networks as cognitive models of English past tense inflection.
Self-Supervised Dialogue Learning.
A Large-Scale Corpus for Conversation Disentanglement.
Pretraining Methods for Dialog Context Representation Learning.
Are Training Samples Correlated? Learning to Generate Dialogue Responses with Multiple References.
Learning to Abstract for Memory-augmented Conversational Response Generation.
Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems.
Proactive Human-Machine Conversation with Explicit Conversation Goal.
On-device Structured and Context Partitioned Projection Networks.
Vocabulary Pyramid Network: Multi-Pass Encoding and Decoding with Multi-Level Vocabularies for Response Generation.
Retrieval-Enhanced Adversarial Training for Neural Response Generation.
Comparison of Diverse Decoding Methods from Conditional Language Models.
Budgeted Policy Learning for Task-Oriented Dialogue Systems.
Dialogue Natural Language Inference.
ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation.
Incremental Learning from Scratch for Task-Oriented Dialogue Systems.
Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention.
Generating Responses with a Specific Emotion in Dialog.
Learning from Dialogue after Deployment: Feed Yourself, Chatbot!
A Just and Comprehensive Strategy for Using NLP to Address Online Abuse.
What Does BERT Learn about the Structure of Language?
Energy and Policy Considerations for Deep Learning in NLP.
Assessing the Ability of Self-Attention Networks to Learn Word Order.
Literary Event Detection.
Shared-Private Bilingual Word Embeddings for Neural Machine Translation.
Improving Visual Question Answering by Referring to Generated Paragraph Captions.
Psycholinguistics Meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering.
Multi-grained Attention with Object-level Grounding for Visual Question Answering.
Generating Question Relevant Captions to Aid Visual Question Answering.
Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension.
ELI5: Long Form Question Answering.
Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network.
Exploring Sequence-to-Sequence Learning in Aspect Term Extraction.
Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text.
Tree Communication Models for Sentiment Analysis.
A Multilingual BPE Embedding Space for Universal Sentiment Lexicon Induction.
Multilingual Constituency Parsing with Self-Attention and Pre-Training.
Women's Syntactic Resilience and Men's Grammatical Luck: Gender-Bias in Part-of-Speech Tagging and Dependency Parsing.
An Imitation Learning Approach to Unsupervised Parsing.
Scalable Syntax-Aware Language Models Using Knowledge Distillation.
Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition.
Zero-Shot Entity Linking by Reading Entity Descriptions.
Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference.
Transforming Complex Sentences into a Semantic Hierarchy.
Decomposable Neural Paraphrase Generation.
EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing.
HighRES: Highlight-based Reference-less Evaluation of Summarization.
Exploring Numeracy in Word Embeddings.
BERT-based Lexical Substitution.
The Effectiveness of Simple Hybrid Systems for Hypernym Discovery.
Embedding Imputation with Grounded Language Information.
Making Fast Graph-based Algorithms with Graph Metric Embeddings.
Putting Words in Context: LSTM Language Models and Lexical Ambiguity.
Annotation and Automatic Classification of Aspectual Categories.
Delta Embedding Learning.
Word and Document Embedding with vMF-Mixture Priors on Context Word Vectors.
Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks.
Unraveling Antonym's Word Vectors through a Siamese-like Network.
Relational Word Embeddings.
Robust Representation Learning of Biomedical Names.
On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings.
Towards Understanding Linear Word Analogies.
Is Word Segmentation Necessary for Deep Learning of Chinese Representations?
Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings.
Unsupervised Joint Training of Bilingual Word Embeddings.
Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections.
JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages.
Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings.
MAAM: A Morphology-Aware Alignment Model for Unsupervised Bilingual Lexicon Induction.
Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization.
Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations.
Zero-Shot Cross-Lingual Abstractive Sentence Summarization through Teaching Generation and Attention.
Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network.
Neural Decipherment via Minimum-Cost Flow: From Ugaritic to Linear B.
CogNet: A Large-Scale Cognate Database.
Choosing Transfer Languages for Cross-Lingual Learning.
Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language Models.
Multi-Source Cross-Lingual Model Transfer: Learning What to Share.
Lattice-Based Transformer Encoder for Neural Machine Translation.
Multilingual Unsupervised NMT using Shared Encoder and Language-Specific Decoders.
Sentence-Level Agreement for Neural Machine Translation.
Leveraging Local and Global Patterns for Self-Attention Networks.
Training Neural Machine Translation to Apply Terminology Constraints.
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation.
A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning.
Robust Neural Machine Translation with Joint Textual and Phonetic Embedding.
Look Harder: A Neural Machine Translation Model with Hard Attention.
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework.
Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation.
Reference Network for Neural Machine Translation.
Domain Adaptation of Neural Machine Translation by Lexicon Induction.
Transformer-XL: Attentive Language Models beyond a Fixed-Length Context.
Interpretable Neural Predictions with Differentiable Binary Variables.
Correlating Neural and Symbolic Representations of Language.
Is Attention Interpretable?
FIESTA: Fast IdEntification of State-of-The-Art models using adaptive bandit algorithms.
Fine-Grained Temporal Relation Extraction.
Matching the Blanks: Distributional Similarity for Relation Learning.
Quantifying Similarity between Relations with Fact Distribution.
Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification.
Open Domain Event Extraction Using Neural Latent Variable Models.
Exploring Author Context for Detecting Intended vs Perceived Sarcasm.
Analyzing Linguistic Differences between Owner and Staff Attributed Tweets.
Who Sides with Whom? Towards Computational Construction of Discourse Networks for Political Debates.
Categorizing and Inferring the Relationship between the Text and Image of Twitter Posts.
CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech.
Joint Effects of Context and User History for Predicting Online Conversation Re-entries.
Putting Evaluation in Context: Contextual Embeddings Improve Machine Translation Evaluation.
Aiming beyond the Obvious: Identifying Non-Obvious Cases in Semantic Similarity Datasets.
We Need to Talk about Standard Splits.
Deep Dominance - How to Properly Compare Deep Neural Models.
Analysis of Automatic Annotation Suggestions for Hard Discourse-Level Tasks in Expert Domains.
Sentence Mover's Similarity: Automatic Evaluation for Multi-Sentence Texts.
Exploiting Explicit Paths for Multi-hop Reading Comprehension.
Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA.
Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension.
Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs.
Cognitive Graph for Multi-Hop Reading Comprehension at Scale.
A Working Memory Model for Task-oriented Dialog Response Generation.
Cross-Modal Commentator: Automatic Machine Commenting Based on Cross-Modal Information.
A Simple Recipe towards Reducing Hallucination in Neural Surface Realisation.
Argument Generation with Retrieval, Planning, and Realization.
Strategies for Structuring Story Generation.
Domain Adaptive Dialog Generation via Meta Learning.
Twitter Homophily: Network Based Prediction of User's Occupation.
Enhancing Air Quality Prediction with Social Media and Natural Language Processing.
Dataset Creation for Ranking Constructive News Comments.
Celebrity Profiling.
Fine-Grained Spoiler Detection from Large-Scale Review Corpora.
Encoding Social Information with Graph Convolutional Networks forPolitical Perspective Detection in News Media.
You Write like You Eat: Stylistic Variation as a Predictor of Social Stratification.
Predicting Human Activities from User-Generated Content.
Sentence-Level Evidence Embedding for Claim Verification with Hierarchical Attention Networks.
Entity-Centric Contextual Affective Analysis.
Multi-task Pairwise Neural Ranking for Hashtag Segmentation.
#YouToo? Detection of Personal Recollections of Sexual Harassment on Social Media.
Topic-Aware Neural Keyphrase Generation for Social Media Language.
Multi-Modal Sarcasm Detection in Twitter with Hierarchical Fusion Model.
Wide-Coverage Neural A* Parsing for Minimalist Grammars.
Graph-based Dependency Parsing with Graph Neural Networks.
Cross-Domain NER using Cross-Domain Language Modeling.
Variance of Average Surprisal: A Better Predictor for Quality of Grammar from Unsupervised PCFG Induction.
Unsupervised Learning of PCFGs with Normalizing Flow.
GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling.
Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies.
Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning.
Head-Driven Phrase Structure Grammar Parsing on Penn Treebank.
Semi-supervised Domain Adaptation for Dependency Parsing.
Compound Probabilistic Context-Free Grammars for Grammar Induction.
XQA: A Cross-lingual Open-domain Question Answering Dataset.
Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension.
Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction.
Generating Question-Answer Hierarchies.
E3: Entailment-driven Extracting and Editing for Conversational Machine Reading.
Multi-Hop Paragraph Retrieval for Open-Domain Question Answering.
Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension.
Multi-style Generative Reading Comprehension.
Explicit Utilization of General Knowledge in Machine Reading Comprehension.
Token-level Dynamic Self-Attention Network for Multi-Passage Reading Comprehension.
Inferential Machine Comprehension: Answering Questions by Recursively Deducing the Evidence Chain from Text.
Unsupervised Rewriter for Multi-Sentence Compression.
On the Summarization of Consumer Health Questions.
Self-Supervised Learning for Contextualized Extractive Summarization.
Ranking Generated Summaries by Correctness: An Interesting but Challenging Application for Natural Language Inference.
BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization.
Adversarial Domain Adaptation Using Artificial Titles for Abstractive Title Generation.
Keep Meeting Summaries on Topic: Abstractive Multi-Modal Meeting Summarization.
Scoring Sentence Singletons and Pairs for Abstractive Summarization.
Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards.
BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization.
Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking.
Improving Abstractive Document Summarization with Salient Information Modeling.
TalkSumm: A Dataset and Scalable Annotation Method for Scientific Paper Summarization Based on Conference Talks.
Reinforced Dynamic Reasoning for Conversational Question Generation.
Learning to Select, Track, and Generate for Data-to-Text.
Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization.
Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models.
Syntax-Infused Variational Autoencoder for Text Generation.
Unsupervised Neural Text Simplification.
Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation.
Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation.
Data-to-text Generation with Entity Modeling.
Towards Fine-grained Text Sentiment Transfer.
Enhancing Topic-to-Essay Generation with External Commonsense Knowledge.
Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation.
PaperRobot: Incremental Draft Generation of Scientific Ideas.
Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding.
Reinforced Training Data Selection for Domain Adaptation.
Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following.
Boosting Entity Linking Performance by Leveraging Unlabeled Documents.
Semi-supervised Stochastic Multi-Domain Learning using Variational Inference.
Continual and Multi-Task Architecture Search.
The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue.
Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video.
Expressing Visual Relationships via Language.
Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation.
Visually Grounded Neural Syntax Acquisition.
Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation.
Self-Supervised Neural Machine Translation.
Generating Diverse Translations with Sentence Codes.
Learning Deep Transformer Models for Machine Translation.
Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation.
Neural Machine Translation with Reordering Embeddings.
Adversarial Multitask Learning for Joint Multi-Feature and Multi-Dialect Morphological Modeling.
Learning Morphosyntactic Analyzers from the Bible via Iterative Annotation Projection across 26 Languages.
Meaning to Form: Measuring Systematicity as Information.
Multilingual Factor Analysis.
SphereRE: Distinguishing Lexical Relations with Hyperspherical Relation Embeddings.
Topic Sensitive Attention on Generic Corpora Corrects Sense Bias in Pretrained Embeddings.
Unsupervised Discovery of Gendered Language through Latent-Variable Modeling.
Understanding Undesirable Word Embedding Associations.
LSTMEmbed: Learning Word and Sense Representations from a Large Semantically Annotated Corpus with Long Short-Term Memories.
Evaluating Gender Bias in Machine Translation.
The Risk of Racial Bias in Hate Speech Detection.
A Transparent Framework for Evaluating Unintended Demographic Bias in Word Embeddings.
Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology.
Gender-preserving Debiasing for Pre-trained Word Embeddings.
Mitigating Gender Bias in Natural Language Processing: Literature Review.
Stochastic Tokenization with a Language Model for Neural Text Classification.
Historical Text Normalization with Delayed Rewards.
Better Character Language Modeling through Morphology.
Using LSTMs to Assess the Obligatoriness of Phonological Distinctive Features for Phonotactic Learning.
Open Vocabulary Learning for Neural Chinese Pinyin IME.
Towards Lossless Encoding of Sentences.
Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization.
Soft Representation Learning for Sparse Transfer.
Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications.
A Lightweight Recurrent Network for Sequence Modeling.
Exact Hard Monotonic Attention for Character-Level Transduction.
On the Robustness of Self-Attentive Models.
Sparse Sequence-to-Sequence Models.
Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks.
Improving Neural Language Models by Segmenting, Attending, and Predicting the Future.
Training Hybrid Language Models by Marginalizing over Segmentations.
Improved Language Modeling by Decoding the Past.
A Neural Multi-digraph Model for Chinese NER with Gazetteers.
Multi-Channel Graph Neural Network for Entity Alignment.
ERNIE: Enhanced Language Representation with Informative Entities.
Multi-grained Named Entity Recognition.
DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction.
GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction.
ARNOR: Attention Regularization based Noise Reduction for Distant Supervision Relation Classification.
Fine-tuning Pre-Trained Transformer Language Models to Distantly Supervised Relation Extraction.
Unsupervised Information Extraction: Regularizing Discriminative Approaches with Relation Distribution Losses.
Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers.
Joint Type Inference on Entities and Relations via Graph Convolutional Networks.
Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data.
Entity-Relation Extraction as Multi-Turn Question Answering.
Graph Neural Networks with Generated Parameters for Relation Extraction.
Global Textual Relation Embedding for Relational Understanding.
Monotonic Infinite Lookback Attention for Simultaneous Machine Translation.
Imitation Learning for Non-Autoregressive Neural Machine Translation.
On the Word Alignment from Neural Machine Translation.
Dynamically Composing Domain-Data Selection with Clean-Data Selection by "Co-Curricular Learning" for Neural Machine Translation.
Syntactically Supervised Transformers for Faster Neural Machine Translation.
Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations.
Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies.
Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation.
Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation.
A Compact and Language-Sensitive Multilingual Translation Method.
When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion.
Self-Attentional Models for Lattice Inputs.
Context-specific Language Modeling for Human Trafficking Detection from Online Advertisements.
Rumor Detection by Exploiting User Credibility Information, Attention and Multi-task Learning.
Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label Distributions.
Poetry to Prose Conversion in Sanskrit as a Linearisation Task: A Case for Low-Resource Languages.
Neural News Recommendation with Topic-Aware News Representation.
Complex Word Identification as a Sequence Labelling Task.
Figurative Usage Detection of Symptom Words to Improve Personal Health Mention Detection.
Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion.
DeepSentiPeer: Harnessing Sentiment in Review Texts to Recommend Peer Review Decisions.
Text Categorization by Learning Predominant Sense of Words as Auxiliary Task.
Heuristic Authorship Obfuscation.
Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency.
Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model.
A Simple Theoretical Model of Importance for Summarization.
Searching for Effective Neural Extractive Summarization: What Works and What's Next.
Global Optimization under Length Constraint for Neural Text Summarization.
Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization.
Argument Invention from First Principles.
Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts.
Multimodal and Multi-view Models for Emotion Recognition.
From Surrogacy to Adoption; From Bitcoin to Cryptocurrency: Debate Topic Expansion.
Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network.
HEAD-QA: A Healthcare Dataset for Complex Reasoning.
Joint Entity Extraction and Assertion Detection for Clinical Text.
Towards Automating Healthcare Question Answering in a Noisy Multilingual Low-Resource Setting.
Finding Your Voice: The Linguistic Development of Mental Health Counselors.
What Makes a Good Counselor? Learning to Distinguish between High-quality and Low-quality Counseling Conversations.
Extracting Symptoms and their Status from Clinical Conversations.
SherLIiC: A Typed Event-Focused Lexical Inference Benchmark for Evaluating Natural Language Inference.
GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification.
Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference.
Knowledge-aware Pronoun Coreference Resolution.
Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing.
OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs.
Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue.
Multi-Task Networks with Universe, Group, and Task Feature Learning.
Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems.
Crowdsourcing and Aggregating Nested Markable Annotations.
Automatic Evaluation of Local Topic Quality.
ChID: A Large-scale Chinese IDiom Dataset for Cloze Test.
DocRED: A Large-Scale Document-Level Relation Extraction Dataset.
Errudite: Scalable, Reproducible, and Testable Error Analysis.
A Wind of Change: Detecting and Evaluating Lexical Semantic Change across Times and Domains.
SP-10K: A Large-scale Evaluation Set for Selectional Preference Acquisition.
How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions.
Just "OneSeC" for Producing Multilingual Sense-Annotated Data.
MOROCO: The Moldavian and Romanian Dialectal Corpus.
A Cross-Domain Transferable Neural Coherence Model.
Coreference Resolution with Entity Equalization.
Implicit Discourse Relation Identification for Open-domain Dialogues.
End-to-end Deep Reinforcement Learning Based Coreference Resolution.
Know What You Don't Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories.
Evaluating Discourse in Structured Text Representations.
Data Programming for Learning Discourse Structure.
Multi-Task Learning for Coherence Modeling.
Learning from Omission.
Topic Tensor Network for Implicit Discourse Relation Recognition in Chinese.
A Corpus for Modeling User and Language Effects in Argumentation on Online Debating.
DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction.
Sentiment Tagging with Partial Labels using Modular Architectures.
Classification and Clustering of Arguments with Contextualized Word Embeddings.
Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis.
Transfer Capsule Network for Aspect Level Sentiment Classification.
Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification.
MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations.
Decompositional Argument Mining: A General Purpose Approach for Argument Graph Construction.
An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis.
Modeling Financial Analysts' Decision Making via the Pragmatics and Semantics of Earnings Calls.
Divide, Conquer and Combine: Hierarchical Feature Fusion Network with Local and Global Perspectives for Multimodal Affective Computing.
Adversarial Attention Modeling for Multi-dimensional Emotion Regression.
Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change.
This Email Could Save Your Life: Introducing the Task of Email Subject Line Generation.
Cross-Sentence Grammatical Error Correction.
Disentangled Representation Learning for Non-Parallel Text Style Transfer.
Evidence-based Trustworthiness.
Detecting Concealed Information in Text and Speech.
What You Say and How You Say It Matters: Predicting Stock Volatility Using Verbal and Vocal Cues.
Neural Text Simplification of Clinical Letters with a Domain Specific Phrase Table.
Towards Unsupervised Text Classification Leveraging Experts and Word Embeddings.
Manipulating the Difficulty of C-Tests.
Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes.
Neural News Recommendation with Long- and Short-term User Representations.
Adaptive Attention Span in Transformers.
Cross-Domain Generalization of Neural Constituency Parsers.
You Only Need Attention to Traverse Trees.
Self-Regulated Interactive Sequence-to-Sequence Learning.
Augmenting Neural Networks with First-order Logic.
Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation.
Relation Embedding with Dihedral Group in Knowledge Graph.
Spatial Aggregation Facilitates Discovery of Spatial Topics.
Attention Guided Graph Convolutional Networks for Relation Extraction.
Neural Relation Extraction for Knowledge Base Enrichment.
Domain Adaptive Inference for Neural Machine Translation.
Revisiting Low-Resource Neural Machine Translation: A Case Study.
Effective Adversarial Regularization for Neural Machine Translation.
An Effective Approach to Unsupervised Machine Translation.
Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces.
Unsupervised Pivot Translation for Distant Languages.
Reliability-aware Dynamic Feature Composition for Name Tagging.
Massively Multilingual Transfer for NER.
A Joint Named-Entity Recognizer for Heterogeneous Tag-sets Using a Tag Hierarchy.
Automatic Generation of High Quality CCGbanks for Parser Domain Adaptation.
The (Non-)Utility of Structural Features in BiLSTM-based Dependency Parsers.
Learning Compressed Sentence Representations for On-Device Text Processing.
Generating Logical Forms from Graph Representations of Text and Entities.
AMR Parsing as Sequence-to-Graph Transduction.
Semantic Expressive Capacity with Bounded Memory.
Semantic Parsing with Dual Learning.
Constructing Interpretive Spatio-Temporal Features for Multi-Turn Responses Selection.
Boosting Dialog Response Generation.
Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study.
Improving Multi-turn Dialogue Modelling with Utterance ReWriter.
Incremental Transformer with Deliberation Decoder for Document Grounded Conversations.
One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues.
