acl 2018 论文列表
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 1: Long Papers.
|
Let's do it "again": A First Computational Approach to Detecting Adverbial Presupposition Triggers.
Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information.
Finding syntax in human encephalography with beam search.
Object-oriented Neural Programming (OONP) for Document Understanding.
Supervised Treebank Conversion: Data and Approaches.
Composing Finite State Transducers on GPUs.
Pre- and In-Parsing Models for Neural Empty Category Detection.
Constituency Parsing with a Self-Attentive Encoder.
Global Transition-based Non-projective Dependency Parsing.
Neural Factor Graph Models for Cross-lingual Morphological Tagging.
Morphosyntactic Tagging with a Meta-BiLSTM Model over Context Sensitive Token Encodings.
A Structured Variational Autoencoder for Contextual Morphological Inflection.
A Purely End-to-End System for Multi-speaker Speech Recognition.
Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game.
Think Visually: Question Answering through Virtual Imagery.
Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning.
On the Automatic Generation of Medical Imaging Reports.
Learning Translations via Images with a Massively Multilingual Image Dataset.
Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning.
Modeling Deliberative Argumentation Strategies on Wikipedia.
Cold-Start Aware User and Product Attention for Sentiment Classification.
A Helping Hand: Transfer Learning for Deep Sentiment Analysis.
Aspect Based Sentiment Analysis with Gated Convolutional Networks.
Cross-Domain Sentiment Classification with Target Domain Specific Information.
Learning Domain-Sensitive and Sentiment-Aware Word Embeddings.
Bilingual Sentiment Embeddings: Joint Projection of Sentiment Across Languages.
Incorporating Glosses into Neural Word Sense Disambiguation.
End-to-End Reinforcement Learning for Automatic Taxonomy Induction.
SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment.
Incorporating Chinese Characters of Words for Lexical Sememe Prediction.
Subword-level Word Vector Representations for Korean.
AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples.
Neural Natural Language Inference Models Enhanced with External Knowledge.
Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval.
hyperdoc2vec: Distributed Representations of Hypertext Documents.
Building Language Models for Text with Named Entities.
Multi-Input Attention for Unsupervised OCR Correction.
Eyes are the Windows to the Soul: Predicting the Rating of Text Quality Using Gaze Behaviour.
Document Similarity for Texts of Varying Lengths via Hidden Topics.
Neural Sparse Topical Coding.
Joint Embedding of Words and Labels for Text Classification.
Disconnected Recurrent Neural Networks for Text Categorization.
A Deep Relevance Model for Zero-Shot Document Filtering.
Modeling Naive Psychology of Characters in Simple Commonsense Stories.
Joint Reasoning for Temporal and Causal Relations.
A Spatial Model for Extracting and Visualizing Latent Discourse Structure in Text.
Discourse Coherence: Concurrent Explicit and Implicit Relations.
Efficient Low-rank Multimodal Fusion With Modality-Specific Factors.
Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph.
Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment.
Efficient Large-Scale Neural Domain Classification with Personalized Attention.
Personalizing Dialogue Agents: I have a dog, do you have pets too?
Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders.
Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning.
Recursive Neural Structural Correspondence Network for Cross-domain Aspect and Opinion Co-Extraction.
Zero-Shot Transfer Learning for Event Extraction.
Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder.
Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning.
What you can cram into a single \$&!#* vector: Probing sentence embeddings for linguistic properties.
To Attend or not to Attend: A Case Study on Syntactic Structures for Semantic Relatedness.
Numeracy for Language Models: Evaluating and Improving their Ability to Predict Numbers.
Token-level and sequence-level loss smoothing for RNN language models.
Marrying Up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding.
Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation.
Syntax for Semantic Role Labeling, To Be, Or Not To Be.
Large-Scale QA-SRL Parsing.
NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing.
Neural Models for Documents with Metadata.
Document Modeling with External Attention for Sentence Extraction.
Semi-supervised User Geolocation via Graph Convolutional Networks.
Multimodal Named Entity Disambiguation for Noisy Social Media Posts.
Visual Attention Model for Name Tagging in Multimodal Social Media.
Rumor Detection on Twitter with Tree-structured Recursive Neural Networks.
Stock Movement Prediction from Tweets and Historical Prices.
NeuralREG: An end-to-end approach to referring expression generation.
Deep-speare: A joint neural model of poetic language, meter and rhyme.
A Distributional and Orthographic Aggregation Model for English Derivational Morphology.
Language Generation via DAG Transduction.
Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification.
Harvesting Paragraph-level Question-Answer Pairs from Wikipedia.
Did the Model Understand the Question?
Training Classifiers with Natural Language Explanations.
Learning How to Actively Learn: A Deep Imitation Learning Approach.
Backpropagating through Structured Argmax using a SPIGOT.
Batch IS NOT Heavy: Learning Word Representations From All Samples.
Sequence-to-sequence Models for Cache Transition Systems.
AMR dependency parsing with a typed semantic algebra.
Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback.
Weakly Supervised Semantic Parsing with Abstract Examples.
How Much Attention Do You Need? A Granular Analysis of Neural Machine Translation Architectures.
Accelerating Neural Transformer via an Average Attention Network.
Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning.
Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings.
Towards Robust Neural Machine Translation.
Question Condensing Networks for Answer Selection in Community Question Answering.
Denoising Distantly Supervised Open-Domain Question Answering.
Efficient and Robust Question Answering from Minimal Context over Documents.
Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension.
Multi-Granularity Hierarchical Attention Fusion Networks for Reading Comprehension and Question Answering.
Stochastic Answer Networks for Machine Reading Comprehension.
DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension.
From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction.
Learning to Generate Move-by-Move Commentary for Chess Games from Large-Scale Social Forum Data.
A Neural Approach to Pun Generation.
Learning to Write with Cooperative Discriminators.
GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data.
A Graph-to-Sequence Model for AMR-to-Text Generation.
Dating Documents using Graph Convolution Networks.
Improving Entity Linking by Modeling Latent Relations between Mentions.
Discovering Implicit Knowledge with Unary Relations.
Higher-order Relation Schema Induction using Tensor Factorization with Back-off and Aggregation.
Nugget Proposal Networks for Chinese Event Detection.
Chinese NER Using Lattice LSTM.
Language Modeling for Code-Mixing: The Role of Linguistic Theory based Synthetic Data.
Isomorphic Transfer of Syntactic Structures in Cross-Lingual NLP.
Embedding Learning Through Multilingual Concept Induction.
Sentiment Adaptive End-to-End Dialog Systems.
Generating Informative Responses with Controlled Sentence Function.
Knowledge Diffusion for Neural Dialogue Generation.
Tailored Sequence to Sequence Models to Different Conversation Scenarios.
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems.
Global-Locally Self-Attentive Encoder for Dialogue State Tracking.
An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking.
Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures.
LSTMs Can Learn Syntax-Sensitive Dependencies Well, But Modeling Structure Makes Them Better.
Twitter Universal Dependency Parsing for African-American and Mainstream American English.
Stack-Pointer Networks for Dependency Parsing.
Distilling Knowledge for Search-based Structured Prediction.
The Hitchhiker's Guide to Testing Statistical Significance in Natural Language Processing.
Automatic Metric Validation for Grammatical Error Correction.
Are BLEU and Meaning Representation in Opposition?
Conversations Gone Awry: Detecting Early Signs of Conversational Failure.
DialSQL: Dialogue Based Structured Query Generation.
Exemplar Encoder-Decoder for Neural Conversation Generation.
A Multi-Axis Annotation Scheme for Event Temporal Relations.
Guess Me if You Can: Acronym Disambiguation for Enterprises.
Learning Prototypical Goal Activities for Locations.
Which Melbourne? Augmenting Geocoding with Maps.
Document Context Neural Machine Translation with Memory Networks.
Context-Aware Neural Machine Translation Learns Anaphora Resolution.
Forest-Based Neural Machine Translation.
A Stochastic Decoder for Neural Machine Translation.
Incorporating Latent Meanings of Morphological Compositions to Enhance Word Embeddings.
Word Embedding and WordNet Based Metaphor Identification and Interpretation.
Searching for the X-Factor: Exploring Corpus Subjectivity for Word Embeddings.
Paraphrase to Explicate: Revealing Implicit Noun-Compound Relations.
Extending a Parser to Distant Domains Using a Few Dozen Partially Annotated Examples.
Gaussian Mixture Latent Vector Grammars.
Straight to the Tree: Constituency Parsing with Neural Syntactic Distance.
Prefix Lexicalization of Synchronous CFGs using Synchronous TAG.
A Framework for Representing Language Acquisition in a Population Setting.
Taylor's law for Human Linguistic Sequences.
MojiTalk: Generating Emotional Responses at Scale.
Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network.
Learning to Control the Specificity in Neural Response Generation.
Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation.
TDNN: A Two-stage Deep Neural Network for Prompt-independent Automated Essay Scoring.
Domain Adaptation with Adversarial Training and Graph Embeddings.
A Neural Architecture for Automated ICD Coding.
Fluency Boost Learning and Inference for Neural Grammatical Error Correction.
Strong Baselines for Neural Semi-Supervised Learning under Domain Shift.
Adaptive Scaling for Sparse Detection in Information Extraction.
Adversarial Contrastive Estimation.
Reasoning with Sarcasm by Reading In-Between.
Working Memory Networks: Augmenting Memory Networks with a Relational Reasoning Module.
Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference.
Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach.
Identifying Transferable Information Across Domains for Cross-domain Sentiment Classification.
Target-Sensitive Memory Networks for Aspect Sentiment Classification.
Transformation Networks for Target-Oriented Sentiment Classification.
What Action Causes This? Towards Naive Physical Action-Effect Prediction.
Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search.
Bridging Languages through Images with Deep Partial Canonical Correlation Analysis.
No Metrics Are Perfect: Adversarial Reward Learning for Visual Storytelling.
Hierarchical Neural Story Generation.
Generating Fine-Grained Open Vocabulary Entity Type Descriptions.
Style Transfer Through Back-Translation.
Semantically Equivalent Adversarial Rules for Debugging NLP models.
Simple and Effective Multi-Paragraph Reading Comprehension.
Multi-Relational Question Answering from Narratives: Machine Reading and Reasoning in Simulated Worlds.
Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge.
Two Methods for Domain Adaptation of Bilingual Tasks: Delightfully Simple and Broadly Applicable.
A Multi-lingual Multi-task Architecture for Low-resource Sequence Labeling.
A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings.
On the Limitations of Unsupervised Bilingual Dictionary Induction.
Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing.
StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing.
Confidence Modeling for Neural Semantic Parsing.
Coarse-to-Fine Decoding for Neural Semantic Parsing.
Classification of Moral Foundations in Microblog Political Discourse.
Mining Cross-Cultural Differences and Similarities in Social Media.
Modeling and Prediction of Online Product Review Helpfulness: A Survey.
Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation.
Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting.
Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization.
Neural Document Summarization by Jointly Learning to Score and Select Sentences.
The price of debiasing automatic metrics in natural language evalaution.
Inherent Biases in Reference-based Evaluation for Grammatical Error Correction.
Give Me More Feedback: Annotating Argument Persuasiveness and Related Attributes in Student Essays.
TutorialBank: A Manually-Collected Corpus for Prerequisite Chains, Survey Extraction and Resource Recommendation.
Not that much power: Linguistic alignment is influenced more by low-level linguistic features rather than social power.
Constraining MGbank: Agreement, L-Selection and Supertagging in Minimalist Grammars.
Entity-Centric Joint Modeling of Japanese Coreference Resolution and Predicate Argument Structure Analysis.
Deep Reinforcement Learning for Chinese Zero Pronoun Resolution.
Coherence Modeling of Asynchronous Conversations: A Neural Entity Grid Approach.
Textual Deconvolution Saliency (TDS) : a deep tool box for linguistic analysis.
Temporal Event Knowledge Acquisition via Identifying Narratives.
Context-Aware Neural Model for Temporal Information Extraction.
Self-regulation: Employing a Generative Adversarial Network to Improve Event Detection.
Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism.
DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction.
Improving Event Coreference Resolution by Modeling Correlations between Event Coreference Chains and Document Topic Structures.
Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis.
Event2Mind: Commonsense Inference on Events, Intents, and Reactions.
ParaNMT-50M: Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations.
Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms.
Discourse Representation Structure Parsing.
Using Intermediate Representations to Solve Math Word Problems.
Accurate SHRG-Based Semantic Parsing.
AMR Parsing as Graph Prediction with Latent Alignment.
Character-Level Models versus Morphology in Semantic Role Labeling.
Multitask Parsing Across Semantic Representations.
Semantic Parsing with Syntax- and Table-Aware SQL Generation.
Improving Text-to-SQL Evaluation Methodology.
Evaluating neural network explanation methods using hybrid documents and morphosyntactic agreement.
Universal Language Model Fine-tuning for Text Classification.
Sentence-State LSTM for Text Representation.
Zero-shot Learning of Classifiers from Natural Language Quantification.
Bridging CNNs, RNNs, and Weighted Finite-State Machines.
Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context.
Graph-to-Sequence Learning using Gated Graph Neural Networks.
Probabilistic Embedding of Knowledge Graphs with Box Lattice Measures.
LinkNBed: Multi-Graph Representation Learning with Entity Linkage.
Retrieval of the Best Counterargument without Prior Topic Knowledge.
A Stylometric Inquiry into Hyperpartisan and Fake News.
Neural Argument Generation Augmented with Externally Retrieved Evidence.
Efficient Online Scalar Annotation with Bounded Support.
A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature.
Comprehensive Supersense Disambiguation of English Prepositions and Possessives.
Obtaining Reliable Human Ratings of Valence, Arousal, and Dominance for 20, 000 English Words.
Simple and Effective Text Simplification Using Semantic and Neural Methods.
Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization.
Extractive Summarization with SWAP-NET: Sentences and Words from Alternating Pointer Networks.
A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss.
Towards Understanding the Geometry of Knowledge Graph Embeddings.
Improving Knowledge Graph Embedding Using Simple Constraints.
Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking.
Ultra-Fine Entity Typing.
The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation.
Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates.
Triangular Architecture for Rare Language Translation.
Unsupervised Neural Machine Translation with Weight Sharing.
Explicit Retrofitting of Distributional Word Vectors.
Unsupervised Learning of Distributional Relation Vectors.
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors.
Probabilistic FastText for Multi-Sense Word Embeddings.
