プログラミングの話じゃないけど、ACL2019のAccepted papersからarXivにもあるものをリストアップしたので、その辺探せば転がってそうだけどせっかくなので共有する。
ACL2019にあるpaper全部を対象としたため、Long, Short, Demo, Studentが含まれる。
その合計が765本で、そのうち316本がarXivに上げられていた（2019年6月18日現在）。
以下、arXivに上がっていたACL論文のリスト。
著者情報とかも簡単に入れられるけど、めんどくさいし個人的にそこまで重要視してないので入れていません。
Long Papers
- Learning from Dialogue after Deployment: Feed Yourself, Chatbot!
- MOROCO: The Moldavian and Romanian Dialectal Corpus
- Improved Language Modeling by Decoding the Past
- Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
- Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings
- Open Vocabulary Learning for Neural Chinese Pinyin IME
- Weakly-Supervised Spatio-Temporally Grounding Natural Sentence in Video
- Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding
- Joint Slot Filling and Intent Detection via Capsule Neural Networks
- This Email Could Save Your Life: Introducing the Task of Email Subject Line Generation
- Incremental Learning from Scratch for Task-Oriented Dialogue Systems
- Latent Variable Model for Multi-modal Translation
- PaperRobot: Incremental Draft Generation of Scientific Ideas
- Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets
- Manipulating the Difficulty of C-Tests
- A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching
- Learning Deep Transformer Models for Machine Translation
- Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model
- Automatic Generation of High Quality CCGbanks for Parser Domain Adaptation
- Multi-Source Cross-Lingual Model Transfer: Learning What to Share
- Identifying Visible Actions in Lifestyle Vlogs
- Augmenting Neural Networks with First-order Logic
- Explicit Utilization of General Knowledge in Machine Reading Comprehension
- DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction
- Self-Attentional Models for Lattice Inputs
- Multi-style Generative Reading Comprehension
- Joint Effects of Context and User History for Predicting Online Conversation Re-entries
- A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings Based on Graph Modularity
- Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension
- Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification
- Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension
- Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing
- Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking
- How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions
- Towards Language Agnostic Universal Representations
- Meaning to Form: Measuring Systematicity as Information
- Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology
- TIGS: An Inference Algorithm for Text Infilling with Gradient Search
- Modeling financial analysts’ decision making via the pragmatics and semantics of earnings calls
- Dialogue Natural Language Inference
- Budgeted Policy Learning for Task-Oriented Dialogue Systems
- An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis
- Extracting Symptoms and their Status from Clinical Conversations
- Comparison of Diverse Decoding Methods from Conditional Language Models
- Retrieval-Enhanced Adversarial Training for Neural Response Generation
- ERNIE: Enhanced Language Representation with Informative Entities
- Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution
- Cognitive Graph for Multi-Hop Reading Comprehension at Scale
- Unsupervised Question Answering by Cloze Translation
- SP-10K: A Large-scale Evaluation Set for Selectional Preference Acquisition
- A Wind of Change: Detecting and Evaluating Lexical Semantic Change across Times and Domains
- Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordances
- Sentence Centrality Revisited for Unsupervised Summarization
- Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
- Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
- Towards Understanding Linear Word Analogies
- When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion
- The Language of Legal and Illegal Activity on the Darknet
- What Kind of Language Is Hard to Language-Model?
- E3: Entailment-driven Extracting and Editing for Conversational Machine Reading
- Analysis of Automatic Annotation Suggestions for Hard Discourse-Level Tasks in Expert Domains
- Word-order biases in deep-agent emergent communication
- Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction
- Entity-Relation Extraction as Multi-Turn Question Answering
- Robust Neural Machine Translation with Doubly Adversarial Inputs
- Improving Neural Language Models by Segmenting, Attending, and Predicting the Future
- A Corpus for Reasoning About Natural Language Grounded in Photographs
- Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning
- Topic-Aware Neural Keyphrase Generation for Social Media Language
- Multi-hop reading comprehension across multiple documents by reasoning over heterogeneous graphs
- Visually Grounded Neural Syntax Acquisition
- Episodic Memory Reader: Learning What to Remember for Question Answering from Streaming Data
- Multimodal Transformer for Unaligned Multimodal Language Sequences
- DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction
- MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations
- Shared-Private Bilingual Word Embeddings for Neural Machine Translation
- Relation Embedding with Dihedral Group in Knowledge Graph
- Multilingual Factor Analysis
- Is Word Segmentation Necessary for Deep Learning of Chinese Representations?
- Interconnected Question Generation with Coreference Alignment and Conversation Flow Modeling
- Data-to-text Generation with Entity Modeling
- DocRED: A Large-Scale Document-Level Relation Extraction Dataset
- MultiQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension
- Cross-Lingual Training for Automatic Question Generation
- Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification
- BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization
- Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies
- GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
- Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems
- Hierarchical Transformers for Multi-Document Summarization
- A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer
- Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation
- ChID: A Large-scale Chinese IDiom Dataset for Cloze Test
- Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies
- Towards Explainable NLP: A Generative Explanation Framework for Text Classification
- Automatic Evaluation of Local Topic Quality
- Are we there yet? Encoder-decoder neural networks as cognitive models of English past tense inflection
- SherLIiC: A Typed Event-Focused Lexical Inference Benchmark for Evaluating Natural Language Inference
- Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards
- Generating Question Relevant Captions to Aid Visual Question Answering
- Continual and Multi-Task Architecture Search
- Adversarial Learning of Privacy-Preserving Text Representations for De-Identification of Medical Records
- The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue
- Handling Divergent Reference Texts when Evaluating Table-to-Text Generation
- Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs
- On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings
- Pretraining Methods for Dialog Context Representation Learning
- Correlating neural and symbolic representations of language
- Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
- Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension
- A Cross-Domain Transferable Neural Coherence Model
- Unsupervised Neural Text Simplification
- Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling
- Fine-Grained Temporal Relation Extraction
- Distant Learning for Entity Linking with Automatic Noise Detection
- AMR Parsing as Sequence-to-Graph Transduction
- Boosting Entity Linking Performance by Leveraging Unlabeled Documents
- Gender-preserving Debiasing for Pre-trained Word Embeddings
- Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text
- Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis
- Like a Baby: Visually Situated Neural Language Acquisition
- Relational Word Embeddings
- Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
- Syntax-Infused Variational Autoencoder for Text Generation
- Generating Logical Forms from Graph Representations of Text and Entities
- Interpretable Neural Predictions with Differentiable Binary Variables
- Symbolic inductive bias for visually grounded learning of spoken language
- Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
- Bridging the Gap between Training and Inference for Neural Machine Translation
- Argument Generation with Retrieval, Planning, and Realization
- Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations
- The (Non-)Utility of Structural Features in BiLSTM-based Dependency Parsers
- Strategies for Structuring Story Generation
- Multi-task Pairwise Neural Ranking for Hashtag Segmentation
- Towards Generating Long and Coherent Text with Multi-Level Latent Variable Models
- Entity-Centric Contextual Affective Analysis
- Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog
- Lattice Transformer for Speech Translation
- Generalized Data Augmentation for Low-Resource Translation
- Probing for Semantic Classes: Diagnosing the Meaning Content of Word Embeddings
- Disentangled Representation Learning for Non-Parallel Text Style Transfer
- HighRES: Highlight-based Reference-less Evaluation of Summarization
- Latent Retrieval for Weakly Supervised Open Domain Question Answering
- Improving Textual Network Embedding with Global Attention via Optimal Transport
- Sentiment Tagging with Partial Labels using Modular Architectures
- Open Domain Event Extraction Using Neural Latent Variable Models
- Choosing Transfer Languages for Cross-Lingual Learning
- Unsupervised Discovery of Gendered Language through Latent-Variable Modeling
- Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks
- Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
- A Unified Linear-Time Framework for Sentence-Level Discourse Parsing
- CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication
- Syntactically Supervised Transformers for Faster Neural Machine Translation
- Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks
- Multi-hop Reading Comprehension through Question Decomposition and Rescoring
- Matching the Blanks: Distributional Similarity for Relation Learning
- Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation
- Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization
- HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization
- Multi-Task Deep Neural Networks for Natural Language Understanding
- Massively Multilingual Transfer for NER
- COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
- Unsupervised Pivot Translation for Distant Languages
- Dynamically Composing Domain-Data Selection with Clean-Data Selection by ``Co-Curricular Learning" for Neural Machine Translation
- Scoring Sentence Singletons and Pairs for Abstractive Summarization
- Scalable Syntax-Aware Language Models Using Knowledge Distillation
- HellaSwag: Can a Machine Really Finish Your Sentence?
- Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks
- Assessing the Ability of Self-Attention Networks to Learn Word Order
- The KnowRef Coreference Corpus: Removing Gender and Number Cues for Difficult Pronominal Anaphora Resolution
- StRE: Self Attentive Edit Quality Prediction in Wikipedia
- Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization
- Dynamically Fused Graph Network for Multi-hop Reasoning
- Towards Multimodal Sarcasm Detection (An Obviously Perfect Paper)
- Curate and Generate: A Corpus and Method for Joint Control of Semantics and Style in Neural NLG
- Variational Pretraining for Semi-supervised Text Classification
- Imitation Learning for Non-Autoregressive Neural Machine Translation
- Domain Adaptive Dialog Generation via Meta Learning
- Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA
- Is Attention Interpretable?
- Exploiting Explicit Paths for Multi-hop Reading Comprehension
- Explain Yourself! Leveraging Language Models for Commonsense Reasoning
- Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation
- Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections
- Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment
- Unified Semantic Parsing with Weak Supervision
- How Large Are Lions? Inducing Distributions over Quantitative Attributes
- Combating Adversarial Misspellings with Robust Word Recognition
- Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
- Training Neural Response Selection for Task-Oriented Dialogue Systems
- Improving Multi-turn Dialogue Modelling with Utterance ReWriter
- Controllable Paraphrase Generation with a Syntactic Exemplar
- Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading
- Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications
- Monotonic Infinite Lookback Attention for Simultaneous Machine Translation
- Domain Adaptation of Neural Machine Translation by Lexicon Induction
- Automatically Identifying Complaints in Social Media
- Matching Article Pairs with Graphical Decomposition and Convolutions
- Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B
- Exploiting Invertible Decoders for Unsupervised Sentence Representation Learning
- Neural Response Generation with Meta-words
- Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good
- An Effective Approach to Unsupervised Machine Translation
- NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
- Transforming Complex Sentences into a Semantic Hierarchy
- Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts
- Time-Out: Temporal Referencing for Robust Modeling of Lexical Semantic Change
- Improving Neural Conversational Models with Entropy-Based Data Filtering
- Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation
- Target-Guided Open-Domain Conversation
- Topic Sensitive Attention on Generic Corpora Corrects Sense Bias in Pretrained Embeddings
- Learning to Ask Unanswerable Questions for Machine Reading Comprehension
- Graph Neural Networks with Generated Parameters for Relation Extraction
- A Lightweight Recurrent Network for Sequence Modeling
- STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework
Short Papers
- Figurative Usage Detection of Symptom Words to Improve Personal Health Mention Detection
- Crowdsourcing and Validating Event-focused Emotion Corpora for German and English
- SemBleu: A Robust Metric for AMR Parsing Evaluation
- Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation
- Robust Neural Machine Translation with Joint Textual and Phonetic Embedding
- The Referential Reader: A Recurrent Entity Network for Anaphora Resolution
- Visual Story Post-Editing
- Adaptive Attention Span in Transformers
- Inter-sentence Relation Extraction with Document-level Graph Convolutional Neural Network
- NNE: A Dataset for Nested Named Entity Recognition in English Newswire
- Misleading Failures of Partial-input Baselines
- Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations
- Exact Hard Monotonic Attention for Character-Level Transduction
- Soft Contextual Data Augmentation for Neural Machine Translation
- How to best use Syntax in Semantic Role Labelling
- Memory Consolidation for Contextual Spoken Language Understanding with Dialogue Logistic Inference
- Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network
- A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning
- CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networks
- An Imitation Learning Approach to Unsupervised Parsing
- Domain Adaptive Inference for Neural Machine Translation
- Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization
- BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization
- Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
- Cost-sensitive Regularization for Label Confusion-aware Event Detection
- Delta Embedding Learning
- Personalizing Dialogue Agents via Meta-Learning
- Fine-Grained Spoiler Detection from Large-Scale Review Corpora
- An Investigation of Transfer Learning-Based Sentiment Analysis in Japanese
- Better Character Language Modeling Through Morphology
- Recognising Agreement and Disagreement between Stances with Reason Comparing Networks
- Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
- Analyzing the limitations of cross-lingual word embedding mappings
- HEAD-QA: A Healthcare Dataset for Complex Reasoning
- Improving Open Information Extraction via Iterative Rank-Aware Learning
- Joint Entity Extraction and Assertion Detection for Clinical Text
- Revisiting Low-Resource Neural Machine Translation: A Case Study
- Putting words in context: LSTM language models and lexical ambiguity
- Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation
- Evaluating Discourse in Structured Text Representations
- Know What You Don't Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories
- Human vs. Muppet: A Conservative Estimate of Human Performance on the GLUE Benchmark
- Context-aware Embedding for Targeted Aspect-based Sentiment Analysis
- Large-Scale Multi-Label Text Classification on EU Legislation
- Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation
- Making Fast Graph-based Algorithms with Graph Metric Embeddings
- Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings
- Neural Legal Judgment Prediction in English
- Dual Supervised Learning for Natural Language Understanding and Generation
- Unsupervised Paraphrasing without Translation
- Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering
- Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings
- Embedding Imputation with Grounded Language Information
- Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning
- Compositional Questions Do Not Necessitate Multi-hop Reasoning
- Learning to Rank for Plausible Plausibility
- Towards Integration of Statistical Hypothesis Tests into Deep Neural Networks
- Why Didn’t You Listen to Me? Comparing User Control of Human-in-the-Loop Topic Models
- Synthetic QA Corpora Generation with Roundtrip Consistency
- Attention-based Conditioning Methods for External Knowledge Integration
- Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation
- Robust Zero-Shot Cross-Domain Slot Filling with Example Values
- Encouraging Paragraph Embeddings to Remember Sentence Identity Improves Classification
- Deep Unknown Intent Detection with Margin Loss
- Training Neural Machine Translation To Apply Terminology Constraints
- BERT Rediscovers the Classical NLP Pipeline
- Exploiting Sentential Context for Neural Machine Translation
- Multilingual Constituency Parsing with Self-Attention and Pre-Training
- Energy and Policy Considerations for Deep Learning in NLP
- Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader
- Evaluating Gender Bias in Machine Translation
- Attention Is (not) All You Need for Commonsense Reasoning
- How Multilingual is Multilingual BERT?
- Global Textual Relation Embedding for Relational Understanding
- Self-Supervised Learning for Contextualized Extractive Summarization
- A Just and Comprehensive Strategy for Using NLP to Address Online Abuse
- Improving Visual Question Answering by Referring to Generated Paragraph Captions
- Towards Lossless Encoding of Sentences
- TalkSumm: A Dataset and Scalable Annotation Method for Scientific Paper Summarization Based on Conference Talks
- A Multi-Task Architecture on Relevance-based Neural Query Translation
- Lattice-Based Transformer Encoder for Neural Machine Translation
- Generating Summaries with Topic Templates and Structured Convolutional Decoders
- Label-Agnostic Sequence Labeling by Copying Nearest Neighbors
- Simultaneous Translation with Flexible Policy via Restricted Imitation Learning
System Demonstration Papers
- Rapid Customization for Event Extraction
- ConvLab: Multi-Domain End-to-End Dialog System Platform
- A Neural, Interactive-predictive System for Multimodal Sequence to Sequence Tasks
- KCAT: A Knowledge-Constraint Typing Annotation Tool
- GLTR: Statistical Detection and Visualization of Generated Text
- OpenKiwi: An Open Source Framework for Quality Estimation
- PerspectroScope: A Window to the World of Diverse Perspectives
- GrapAL: Connecting the Dots in Scientific Literature
- Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation
- Parallax: Visualizing and Understanding the Semantics of Embedding Spaces via Algebraic Formulae
Student Research Workshop Papers
- A computational linguistic study of personal recovery in bipolar disorder
- A Strong and Robust Baseline for Text-Image Matching
- Enriching Neural Models with Targeted Features for Dementia Detection
- Multimodal Logical Inference System for Visual-Textual Entailment
- Multiple Character Embeddings for Chinese Word Segmentation
- Paraphrases as Foreign Languages in Multilingual Neural Machine Translation
- Reducing Gender Bias in Word-Level Language Models with A Gender-Equalizing Loss Function