Language Information Processing

General

• Generating Sentences from a Continuous Space
• Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
• Using the Output Embedding to Improve Language Models
• Hierarchical Multiscale Recurrent Neural Networks
• Efficient softmax approximation for GPUs
• Neural Models for Sequence Chunking
• Improved Variational Autoencoders for Text Modeling using Dilated Convolutions
• Interactive Natural Language Acquisition in a Multi-modal Recurrent Neural Architecture
• Machine Learning on Sequential Data Using a Recurrent Weighted Average
• Linguistic Knowledge as Memory for Recurrent Neural Networks
• Improved Training of Wasserstein GANs
• Learning to Skim Text
• Supervised Learning of Universal Sentence Representations from Natural Language Inference Data (InferSent)
• Poincaré Embeddings for Learning Hierarchical Representations
• Neural Embeddings of Graphs in Hyperbolic Space
• Adversarial Generation of Natural Language
• One button machine for automating feature engineering in relational databases
• Natural Language Processing with Small Feed-Forward Networks
• Dynamic Entity Representations in Neural Language Models
• A Feature-Rich Vietnamese Named-Entity Recognition Model

Language Modeling

• Improving Language Modeling using Densely Connected Recurrent Neural Networks
• Frustratingly Short Attention Spans in Neural Language Modeling
• Improving Neural Language Models with a Continuous Cache
• Online Representation Learning in Recurrent Neural Language Models
• Neural Lattice Language Models

Translation

• A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation
• Chunk-Based Bi-Scale Decoder for Neural Machine Translation
• Attention Is All You Need
• Depthwise Separable Convolutions for Neural Machine Translation
• Confidence through Attention
• Unsupervised Neural Machine Translation

Sentence Embedding / Classification / Matching

• Neural Semantic Encoders
• Match-Tensor: a Deep Relevance Model for Search
• A Structured Self-attentive Sentence Embedding
• Learning to Generate Reviews and Discovering Sentiment
• Jointly Learning Sentence Embeddings and Syntax with Unsupervised Tree-LSTMs
• An Attention Mechanism for Answer Selection Using a Combined Global and Local View
• Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference
• Sentence-State LSTM for Text Representation

Memory Networks

• End-To-End Memory Networks
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
• DMN+ Dynamic Memory Networks for Visual and Textual Question Answering
• Hierarchical Attention Networks for Document Classification
• Tracking the World State with Recurrent Entity Networks
• Working Memory Networks: Augmenting Memory Networks with a Relational Reasoning Module

RC / QA / Information Retrieval

• A Comparative Study of Word Embeddings for Reading Comprehension
• A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
• Gated-Attention Readers for Text Comprehension
• Attention-over-Attention Neural Networks for Reading Comprehension
• Question Answering from Unstructured Text by Retrieval and Comprehension
• Query-Reduction Networks for Question Answering
• Reasoning with Memory Augmented Neural Networks for Language Comprehension
• R-NET: Machine Reading Comprehension with Self-matching Networks
• Consensus Attention-based Neural Networks for Chinese Reading Comprehension
• Ruminating Reader: Reasoning with Gated Multi-Hop Attention
• Learning to Ask: Neural Question Generation for Reading Comprehension
• TableQA: Question Answering on Tabular Data
• S-Net: From Answer Extraction to Answer Generation for Machine Reading Comprehension
• Toward Incorporation of Relevant Documents in word2vec
• Question Dependent Recurrent Entity Network for Question Answering
• HyperQA: Hyperbolic Embeddings for Fast and Efficient Ranking of Question Answer Pairs
• Globally Normalized Reader
• Stochastic Answer Networks for Machine Reading Comprehension
• Adaptive Memory Networks
• Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension

Dialogue

• A Neural Conversational Model
• On-line Active Reward Learning for Policy Optimization in Spoken Dialogue Systems
• Deep Reinforcement Learning for Dialogue Generation
• Learning through Dialogue Interactions by Asking Questions
• Generating Long and Diverse Responses with Neural Conversation Models
• Learning to Decode for Future Success
• A Knowledge-Grounded Neural Conversation Model
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Composite Task-Completion Dialogue System via Hierarchical Deep Reinforcement Learning
• Not All Dialogues are Created Equal: Instance Weighting for Neural Conversational Models
• Improving Frame Semantic Parsing with Hierarchical Dialogue Encoders
• Natural Language Generation for Spoken Dialogue System using RNN Encoder-Decoder Networks
• Key-Value Retrieval Networks for Task-Oriented Dialogue
• Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
• Sub-domain Modelling for Dialogue Managementwith Hierarchical Reinforcement Learning
• Learning to Query, Reason, and Answer Questions On Ambiguous Texts

Summarization / Generative

• A Neural Attention Model for Abstractive Sentence Summarization
• CopyNet Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• Get To The Point: Summarization with Pointer-Generator Networks
• A Deep Reinforced Model for Abstractive Summarization
• Controlling Linguistic Style Aspects in Neural Language Generation
• Deep Recurrent Generative Decoder for Abstractive Text Summarization
• Generating Sentences Using a Dynamic Canvas

Chinese Word Segmentation / NER

• Neural Word Segmentation Learning for Chinese
• Transfer Learning for Low-Resource Chinese Word Segmentation with a Novel Neural Network
• Learning Character Representations for Chinese Word Segmentation
• Fast and Accurate Neural Word Segmentation for Chinese
• Improving Semantic Relevance for Sequence-to-Sequence Le arning of Chinese Social Media Text Summarization
• Dual Long Short-Term Memory Networks for Sub-Character Representation Learning
• Chinese NER Using Lattice LSTM

Embedding

• An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation
• Learning to Compute Word Embeddings On the Fly
• Context Aware Document Embedding
• Neural Bag-of-Ngrams
• Learning Chinese Word Representations From Glyphs Of Characters
• One-shot and few-shot learning of word embeddings

Time series

• Variational Inference for On-line Anomaly Detection in High-Dimensional Time Series

Others

• Numerically Grounded Language Models for Semantic Error Correction
• Iterative Multi-document Neural Attention for Multiple Answer Prediction
• Content-Based Table Retrieval for Web Queries
• On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis
• Joint Event Extraction via Recurrent Neural Networks
• End-to-End Information Extraction without Token-Level Supervision
• DocTag2Vec: An Embedding Based Multi-label Learning Approach for Document Tagging
• Integrating Lexical and Temporal Signals in Neural Ranking Models for Searching Social Media Streams
• Learning to Attend, Copy, and Generate for Session-Based Query Suggestion