emnlp 2017 论文列表
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017.
|
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints.
Depression and Self-Harm Risk Assessment in Online Forums.
Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog.
Bringing Structure into Summaries: Crowdsourcing a Benchmark Corpus of Concept Maps.
Zipporah: a Fast and Scalable Data Cleaning System for Noisy Web-Crawled Parallel Corpora.
Topic-Based Agreement and Disagreement in US Electoral Manifestos.
Truth of Varying Shades: Analyzing Language in Fake News and Political Fact-Checking.
Using Automated Metaphor Identification to Aid in Detection and Prediction of First-Episode Schizophrenia.
Charmanteau: Character Embedding Models For Portmanteau Creation.
DOC: Deep Open Classification of Text Documents.
Learning what to read: Focused machine reading.
A Simple Regularization-based Algorithm for Learning Cross-Domain Word Embeddings.
Analogs of Linguistic Structure in Deep Representations.
Deep Multi-Task Learning for Aspect Term Extraction with Memory Interaction.
Natural Language Processing with Small Feed-Forward Networks.
The strange geometry of skip-gram with negative sampling.
No Need to Pay Attention: Simple Recurrent Neural Networks Work!
Sequence Effects in Crowdsourced Annotations.
Visual Denotations for Recognizing Textual Entailment.
Neural Machine Translation with Source Dependency Representation.
Image Pivoting for Learning Multilingual Multimodal Representations.
Cross-Lingual Transfer Learning for POS Tagging without Cross-Lingual Resources.
Exploiting Cross-Sentence Context for Neural Machine Translation.
Sharp Models on Dull Hardware: Fast and Accurate Neural Machine Translation Decoding on the CPU.
A Study of Style in Machine Translation: Controlling the Formality of Machine Translation Output.
Adapting Sequence Models for Sentence Correction.
Neural Sequence-Labelling Models for Grammatical Error Correction.
Transition-Based Disfluency Detection using LSTMs.
An Empirical Analysis of Edit Importance between Document Versions.
Identifying the Provision of Choices in Privacy Policy Text.
A Novel Cascade Model for Learning Latent Similarity from Heterogeneous Sequential Data of MOOC.
Detecting and Explaining Causes From Text For a Time Series Event.
Identifying Semantically Deviating Outlier Documents.
Quantifying the Effects of Text Duplication on Semantic Models.
Learning to Predict Charges for Criminal Cases with Legal Basis.
Multi-modular domain-tailored OCR post-correction.
A Simpler and More Generalizable Story Detector using Verb and Character Features.
Word Etymology as Native Language Interference.
An Insight Extraction System on BioMedical Literature with Deep Neural Networks.
Entity Linking via Joint Encoding of Types, Descriptions, and Context.
Fast and Accurate Entity Recognition with Iterated Dilated Convolutions.
Leveraging Linguistic Structures for Named Entity Recognition with Bidirectional Recursive Neural Networks.
Speeding up Reinforcement Learning-based Information Extraction Training using Asynchronous Methods.
NITE: A Neural Inductive Teaching Framework for Domain Specific NER.
Scientific Information Extraction with Semi-supervised Neural Tagging.
MinIE: Minimizing Facts in Open Information Extraction.
Deep Joint Entity Disambiguation with Local Neural Attention.
Labeling Gaps Between Words: Recognizing Overlapping Mentions with Mention Separators.
Identifying Products in Online Cybercrime Marketplaces: A Dataset for Fine-grained Domain Adaptation.
Improving Slot Filling Performance with Attentive Neural Networks on Dependency Structures.
Learning Fine-grained Relations from Chinese User Generated Categories.
Counterfactual Learning from Bandit Feedback under Deterministic Logging : A Case Study in Statistical Machine Translation.
Classification of telicity using cross-linguistic annotation projection.
Cross-Lingual Induction and Transfer of Verb Classes Based on Word Vector Space Specialisation.
Cheap Translation for Cross-Lingual Named Entity Recognition.
Learning Language Representations for Typology Prediction.
Identifying Cognate Sets Across Dictionaries of Related Languages.
Deciphering Related Languages.
Machine Translation, it's a question of style, innit? The case of English tag questions.
Knowledge Distillation for Bilingual Dictionary Induction.
A Challenge Set Approach to Evaluating Machine Translation.
Further Investigation into Reference Bias in Monolingual Evaluation of Machine Translation.
Towards Debate Automation: a Recurrent Model for Predicting Debate Winners.
Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning.
Deal or No Deal? End-to-End Learning of Negotiation Dialogues.
Does syntax help discourse segmentation? Not so much.
Investigating Different Syntactic Context Types and Context Representations for Learning Word Embeddings.
Part-of-Speech Tagging for Twitter with Adversarial Neural Networks.
Repeat before Forgetting: Spaced Repetition for Efficient and Effective Training of Neural Networks.
Learning Generic Sentence Representations Using Convolutional Neural Networks.
The Impact of Modeling Overall Argumentation with Tree Kernels.
Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision.
Never Abandon Minorities: Exhaustive Extraction of Bursty Phrases on Microblogs Using Set Cover Problem.
Assessing Objective Recommendation Quality through Political Forecasting.
Topic Signatures in Political Campaign Speeches.
Controlling Human Perception of Basic User Traits.
Connotation Frames of Power and Agency in Modern Films.
Distinguishing Japanese Non-standard Usages from Standard Ones.
Argument Mining on Twitter: Arguments, Facts and Sources.
Dimensions of Interpersonal Relationships: Corpus and Experiments.
A Factored Neural Network Model for Characterizing Online Discussions in Vector Space.
Demographic-aware word associations.
Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction.
All that is English may be Hindi: Enhancing language identification through automatic ranking of the likeliness of word borrowing in social media.
Challenges in Data-to-Document Generation.
Why We Need New Evaluation Metrics for NLG.
Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning.
Bootstrapping incremental dialogue systems from minimal data: the generalisation power of dialogue grammars.
Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models.
Affordable On-line Dialogue Policy Learning.
Towards Implicit Content-Introducing for Generative Short-Text Conversation Systems.
Modeling Dialogue Acts with Content Word Filtering and Speaker Preferences.
Using Context Information for Dialog Act Classification in DNN Framework.
Adversarial Learning for Neural Dialogue Generation.
Preserving Distributional Information in Dialogue Act Classification.
Steering Output Style and Topic in Neural Response Generation.
When to Finish? Optimal Beam Search for Neural Text Generation (modulo beam size).
Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events.
Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank.
Towards Automatic Construction of News Overview Articles by News Synthesis.
Extractive Summarization Using Multi-Task Learning with Document Classification.
Deep Recurrent Generative Decoder for Abstractive Text Summarization.
Cascaded Attention based Unsupervised Information Distillation for Compressive Summarization.
Break it Down for Me: A Study in Automated Lyric Annotation.
Identifying Where to Focus in Reading Comprehension for Neural Question Generation.
What is the Essence of a Claim? Cross-Domain Claim Identification.
Document-Level Multi-Aspect Sentiment Classification as Machine Comprehension.
Reasoning with Heterogeneous Knowledge for Commonsense Machine Comprehension.
Adversarial Examples for Evaluating Reading Comprehension Systems.
Accurate Supervised and Semi-Supervised Machine Reading for Long Documents.
Identifying Semantic Edit Intentions from Revisions in Wikipedia.
Fine Grained Citation Span for References in Wikipedia.
Satirical News Detection and Analysis using Attention Mechanism and Linguistic Features.
Trainable Greedy Decoding for Neural Machine Translation.
Graph Convolutional Encoders for Syntax-aware Neural Machine Translation.
Unfolding and Shrinking Neural Machine Translation Ensembles.
Earth Mover's Distance Minimization for Unsupervised Bilingual Lexicon Induction.
CROWD-IN-THE-LOOP: A Hybrid Approach for Annotating Semantic Roles.
Finding Patterns in Noisy Crowds: Regression-based Annotation Aggregation for Crowdsourced Data.
Adapting Topic Models using Lexical Associations with Tree Priors.
Shortest-Path Graph Kernels for Document Similarity.
Initializing Convolutional Filters with Semantic Features for Text Classification.
Inducing Semantic Micro-Clusters from Deep Multi-View Representations of Novels.
Syllable-aware Neural Language Models: A Failure to Beat Character-aware Ones.
A Simple Language Model based on PMI Matrix Approximations.
Reference-Aware Language Models.
Towards Quantum Language Models.
Dynamic Entity Representations in Neural Language Models.
Temporal dynamics of semantic relations in word embeddings: an application to predicting armed conflict participants.
Exploring Vector Spaces for Semantic Relations.
Noise-Clustered Distant Supervision for Relation Extraction: A Nonparametric Bayesian Perspective.
Deep Residual Learning for Weakly-Supervised Relation Extraction.
A Sequential Model for Classifying Temporal Relations between Intra-Sentence Events.
A Soft-label Method for Noise-tolerant Distantly Supervised Relation Extraction.
Context-Aware Representations for Knowledge Base Relation Extraction.
Adversarial Training for Relation Extraction.
Incorporating Relation Paths in Neural Relation Extraction.
Dual Tensor Model for Detecting Asymmetric Lexico-Semantic Relations.
Sparsity and Noise: Where Knowledge Graph Embeddings Fall Short.
KGEval: Accuracy Estimation of Automatically Constructed Knowledge Graphs.
End-to-End Neural Relation Extraction with Global Optimization.
Global Normalization of Convolutional Neural Networks for Joint Entity and Relation Classification.
TAG Parsing with Neural Networks and Vector Representations of Supertags.
Semi-supervised Structured Prediction with Neural CRF Autoencoder.
Effective Inference for Generative Neural Parsing.
Combining Generative and Discriminative Approaches to Unsupervised Dependency Parsing via Dual Decomposition.
Dependency Grammar Induction with Neural Lexicalization and Big Training Data.
Stack-based Multi-layer Attention for Transition-based Dependency Parsing.
Neural Discontinuous Constituency Parsing.
Incremental Graph-based Neural Dependency Parsing.
Efficient Discontinuous Phrase-Structure Parsing via the Generalized Maximum Spanning Arborescence.
CRF Autoencoder for Unsupervised Dependency Parsing.
Opinion Recommendation Using A Neural Model.
Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm.
Story Comprehension for Predicting What Happens Next.
A Question Answering Approach for Emotion Cause Extraction.
"i have a feeling trump will win..................": Forecasting Winners and Losers from User Predictions on Twitter.
Detecting Perspectives in Political Debates.
Asking too much? The rhetorical role of questions in political discourse.
Identifying civilians killed by police with distantly supervised entity-event extraction.
Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection.
Joint Concept Learning and Semantic Parsing from Natural Language Explanations.
Neural Semantic Parsing with Type Constraints for Semi-Structured Tables.
Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling.
Using Target-side Monolingual Data for Neural Machine Translation through Multi-task Learning.
Source-Side Left-to-Right or Target-Side Left-to-Right? An Empirical Comparison of Two Phrase-Based Decoding Algorithms.
Regularization techniques for fine-tuning in neural machine translation.
Instance Weighting for Neural Machine Translation Domain Adaptation.
Towards Compact and Fast Neural Machine Translation Using a Combined Method.
Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback.
Learning Translations via Matrix Completion.
Towards Bidirectional Hierarchical Representations for Attention-based Neural Machine Translation.
Translating Phrases in Neural Machine Translation.
Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search.
Dynamic Data Selection for Neural Machine Translation.
Memory-augmented Neural Machine Translation.
Neural Lattice-to-Sequence Models for Uncertain Inputs.
Identifying attack and support argumentative relations using deep learning.
Here's My Point: Joint Pointer Architecture for Argument Mining.
Using Argument-based Features to Predict and Analyse Review Helpfulness.
Patterns of Argumentation Strategies across Topics.
GRASP: Rich Patterns for Argumentation Mining.
Learning to Rank Semantic Coherence for Topic Segmentation.
Revisiting Selectional Preferences for Coreference Resolution.
What is it? Disambiguating the different readings of the pronoun 'it'.
How much progress have we made on RST discourse parsing? A replication study of recent results on the RST-DT.
Chinese Zero Pronoun Resolution with Deep Memory Network.
Multi-task Attention-based Neural Networks for Implicit Discourse Relationship Representation and Identification.
Learning Contextually Informed Representations for Linear-Time Discourse Parsing.
Predicting Word Association Strengths.
An End-to-End Deep Framework for Answer Triggering with a Novel Group-Level Objective.
AMR Parsing using Stack-LSTMs.
Getting the Most out of AMR Parsing.
A Joint Sequential and Relational Model for Frame-Semantic Parsing.
Cross-domain Semantic Parsing via Paraphrasing.
A Continuously Growing Dataset of Sentential Paraphrases.
Macro Grammars and Holistic Triggering for Efficient Semantic Parsing.
Idiom-Aware Compositional Distributed Semantics.
A Short Survey on Taxonomy Learning from Text Corpora: Issues, Resources and Recent Advances.
Inter-Weighted Alignment Network for Sentence Pair Modeling.
Learning Word Relatedness over Time.
Neural Sequence Learning Models for Word Sense Disambiguation.
Human Centered NLP with User-Factor Adaptation.
Outta Control: Laws of Semantic Change and Inherent Biases in Word Representation Models.
Deeper Attention to Abusive User Content Moderation.
ConStance: Modeling Annotation Contexts to Improve Stance Classification.
Tensor Fusion Network for Multimodal Sentiment Analysis.
Multi-modal Summarization for Asynchronous Collection of Text, Image, Audio and Video.
Speaking, Seeing, Understanding: Correlating semantic models with conceptual representation in the brain.
Speech segmentation with a neural encoder model of working memory.
Globally Normalized Reader.
PACRR: A Position-Aware Neural IR Model for Relevance Matching.
Importance sampling for unbiased on-demand evaluation of knowledge base population.
A Structured Learning Approach to Temporal Relation Extraction.
An analysis of eye-movements during reading for the detection of mild cognitive impairment.
Mapping Instructions and Visual Observations to Actions with Reinforcement Learning.
Incorporating Global Visual Features into Attention-based Neural Machine Translation.
Evaluating Hierarchies of Verb Argument Structure with Hierarchical Clustering.
Reinforced Video Captioning with Entailment Rewards.
Video Highlight Prediction Using Audience Chat Reactions.
Hierarchically-Attentive RNN for Album Summarization and Storytelling.
Deriving continous grounded meaning representations from referentially structured multimodal contexts.
Zero-Shot Activity Recognition with Verb Attribute Induction.
Guided Open Vocabulary Image Captioning with Constrained Beam Search.
The Promise of Premise: Harnessing Question Premises in Visual Question Answering.
Sound-Word2Vec: Learning Word Representations Grounded in Sounds.
An empirical study on the effectiveness of images in Multimodal Neural Machine Translation.
Recovering Question Answering Errors via Query Revision.
Ranking Kernels for Structures and Embeddings: A Hybrid Preference and Classification Model.
Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecture.
Learning to Paraphrase for Question Answering.
Question Generation for Question Answering.
Latent Space Embedding for Retrieval in Question-Answer Archives.
Deep Neural Solver for Math Word Problems.
Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension.
World Knowledge for Reading Comprehension: Rare Entity Prediction with Hierarchical LSTMs Using External Descriptions.
Structural Embedding of Syntactic Trees for Machine Comprehension.
Learning Fine-Grained Expressions to Solve Math Word Problems.
Beyond Sentential Semantic Parsing: Tackling the Math SAT with a Cascade of Tree Transducers.
RACE: Large-scale ReAding Comprehension Dataset From Examinations.
From Textbooks to Knowledge: A Case Study in Harvesting Axiomatic Knowledge from Textbooks to Solve Geometry Problems.
Segmentation-Free Word Embedding for Unsegmented Languages.
Word-Context Character Embeddings for Chinese Word Segmentation.
Cross-lingual Character-Level Neural Morphological Tagging.
The Labeled Segmentation of Printed Books.
Do LSTMs really work so well for PoS tagging? - A replication study.
A Sub-Character Architecture for Korean Language Processing.
Paradigm Completion for Derivational Morphology.
Don't Throw Those Morphological Analyzers Away Just Yet: Neural Morphological Disambiguation for Arabic.
Multi-Grained Chinese Word Segmentation.
Determining Semantic Textual Similarity using Natural Deduction Proofs.
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data.
SCDV : Sparse Composite Document Vectors using soft clustering over distributional representations.
Measuring Thematic Fit with Distributional Feature Overlap.
Filling the Blanks (hint: plural noun) for Mad Libs Humor.
A Hybrid Convolutional Variational Autoencoder for Text Generation.
Neural Response Generation via GAN with an Approximate Embedding Layer.
Split and Rephrase.
Learning how to Active Learn: A Deep Reinforcement Learning Approach.
Sentence Simplification with Deep Reinforcement Learning.
Task-Oriented Query Reformulation with Reinforcement Learning.
DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning.
Sentiment Lexicon Expansion Based on Neural PU Learning, Double Dictionary Lookup, and Polarity Association.
Sentiment Intensity Ranking among Adjectives Using Sentiment Bearing Word Embeddings.
A Multilayer Perceptron based Ensemble Technique for Fine-grained Financial Sentiment Analysis.
Refining Word Embeddings for Sentiment Analysis.
Identifying and Tracking Sentiments and Topics from Social Media Texts during Natural Disasters.
Capturing User and Product Information for Document Level Sentiment Analysis with Deep Memory Network.
Towards a Universal Sentiment Classifier in Multiple languages.
Sentiment Lexicon Construction with Representation Learning Based on Hierarchical Sentiment Supervision.
Identifying Humor in Reviews using Background Text Sources.
Magnets for Sarcasm: Making Sarcasm Detection Timely, Contextual and Very Personal.
Author-aware Aspect Topic Sentiment Model to Retrieve Supporting Opinions from Reviews.
A Cognition Based Attention Model for Sentiment Analysis.
Recurrent Attention Network on Memory for Aspect Sentiment Analysis.
Why ADAGRAD Fails for Online Topic Modeling.
A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks.
Sparse Communication for Distributed Gradient Descent.
Learning the Structure of Variable-Order CRFs: a finite-state perspective.
Piecewise Latent Variables for Neural Variational Text Processing.
A causal framework for explaining the predictions of black-box sequence-to-sequence models.
Rotated Word Vector Representations and their Interpretability.
Efficient Attention using a Fixed-Size Memory Representation.
Unsupervised Pretraining for Sequence to Sequence Learning.
Learning to select data for transfer learning with Bayesian Optimization.
Incremental Skip-gram Model with Negative Sampling.
Learning What's Easy: Fully Differentiable Neural Easy-First Taggers.
Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging.
MUSE: Modularizing Unsupervised Sense Embeddings.
Word Re-Embedding via Manifold Dimensionality Retention.
VecShare: A Framework for Sharing Word Representation Vectors.
Word Embeddings based on Fixed-Size Ordinally Forgetting Encoding.
High-risk learning: acquiring new word vectors from tiny data.
Exploiting Word Internal Structures for Generic Chinese Sentence Representation.
Exploiting Morphological Regularities in Distributional Word Representations.
Joint Embeddings of Chinese Words, Characters, and Fine-grained Subcharacter Components.
Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext.
Learning Chinese Word Representations From Glyphs Of Characters.
Dict2vec : Learning Word Embeddings using Lexical Dictionaries.
Ngram2vec: Learning Improved Word Representations from Ngram Co-occurrence Statistics.
Hierarchical Embeddings for Hypernymy Detection and Directionality.
A Mention-Ranking Model for Abstract Anaphora Resolution.
Affinity-Preserving Random Walk for Multi-Document Summarization.
Neural Net Models of Open-domain Discourse Coherence.
End-to-end Neural Coreference Resolution.
Obj2Text: Generating Visually Descriptive Language from Object Layouts.
Continuous Representation of Location for Geolocation and Lexical Dialectology using Mixture Density Networks.
Where is Misty? Interpreting Spatial Descriptors by Modeling Regions in Space.
Towards Decoding as Continuous Optimisation in Neural Machine Translation.
Neural Machine Translation with Word Predictions.
Neural Machine Translation with Source-Side Latent Graph Parsing.
Past, Present, Future: A Computational Investigation of the Typology of Tense in 1000 Languages.
Mimicking Word Embeddings using Subword RNNs.
Universal Semantic Parsing.
Train-O-Matic: Large-Scale Supervised Word Sense Disambiguation in Multiple Languages without Manual Training Data.
Entity Linking for Queries by Searching Wikipedia Sentences.
Integrating Order Information and Event Relation for Script Event Prediction.
Heterogeneous Supervision for Relation Extraction: A Representation Learning Approach.
Position-aware Attention and Supervised Data Improve Slot Filling.
Quasi-Second-Order Parsing for 1-Endpoint-Crossing, Pagenumber-2 Graphs.
Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set.
Monolingual Phrase Alignment on Parse Forests.