wovepaper — the arXiv observatory

The paper introduces an unsupervised approach to train recurrent neural network grammars using amortized variational inference with a neural CRF constituency parser, achieving lang…

Publications (72)

Ontology-Aware Token Embeddings for Prepositional Phrase Attachment

Correlation-based Intrinsic Evaluation of Word Vector Representations

Transition-Based Dependency Parsing with Stack Long Short-Term Memory

Dynamic Integration of Background Knowledge in Neural NLU Systems

Unsupervised Text Style Transfer using Language Models as Discriminators

Scalable Syntax-Aware Language Models Using Knowledge Distillation

Document Context Language Models

Learning to Compose Words into Sentences with Reinforcement Learning

Unsupervised Recurrent Neural Network Grammars

Reference-Aware Language Models

A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models

Sparse Overcomplete Word Vector Representations

Generalizing and Hybridizing Count-based and Neural Language Models

Character-based Neural Machine Translation

Training with Exploration Improves a Greedy Stack-LSTM Parser

Problems With Evaluation of Word Embeddings Using Word Similarity Tasks

Non-distributional Word Vector Representations

An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search

Cross-lingual Models of Word Embeddings: An Empirical Comparison

DyNet: The Dynamic Neural Network Toolkit

Sentence Encoding with Tree-constrained Relation Networks

A framework for (under)specifying dependency syntax without overloading annotators

Semantic Parsing with Semi-Supervised Sequential Autoencoders

Recurrent Neural Network Grammars

Paraphrase-Supervised Models of Compositionality

Minimum Error Rate Training and the Convex Hull Semiring

Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling

Incorporating Structural Alignment Biases into an Attentional Neural Translation Model

Morphological Inflection Generation Using Character Sequence to Sequence Learning

Learning Word Representations with Hierarchical Sparse Coding

Learning the Curriculum with Bayesian Optimization for Task-Specific Word Representation Learning

Modeling Dynamic Relationships Between Characters in Literary Novels

The Neural Noisy Channel

The NarrativeQA Reading Comprehension Challenge

Language Modeling with Power Low Rank Ensembles

Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning

Unsupervised POS Induction with Word Embeddings

Massively Multilingual Word Embeddings

Relational inductive biases, deep learning, and graph networks

Neural Arithmetic Logic Units

Notes on Noise Contrastive Estimation and Negative Sampling

Distilling an Ensemble of Greedy Dependency Parsers into One MST Parser

Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs

Many Languages, One Parser

Semantic Scan: Detecting Subtle, Spatially Localized Events in Text Streams

Segmental Recurrent Neural Networks

Depth-Gated LSTM

Learning and Evaluating General Linguistic Intelligence

Learning to Discover, Ground and Use Words with Segmental Neural Language Models

Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold

Retrofitting Word Vectors to Semantic Lexicons

Conditional Random Field Autoencoders for Unsupervised Structured Prediction

Finding Syntax in Human Encephalography with Beam Search

Syntactic Scaffolds for Semantic Structures

Multitask Learning with CTC and Segmental CRF for Speech Recognition

Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems

Generative and Discriminative Text Classification with Recurrent Neural Networks

Segmental Recurrent Neural Networks for End-to-end Speech Recognition

Differentiable Scheduled Sampling for Credit Assignment

End-to-End Neural Segmental Models for Speech Recognition

Learning to Represent Words in Context with Multilingual Supervision

Pushing the bounds of dropout

Learning Deep Generative Models of Graphs

Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation

On the State of the Art of Evaluation in Neural Language Models

Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs

Predicting the NFL using Twitter

Fast Parametric Learning with Activation Memorization

On-the-fly Operation Batching in Dynamic Computation Graphs

Neural Machine Translation with Recurrent Attention Modeling

Neural Architectures for Named Entity Recognition

What Do Recurrent Neural Network Grammars Learn About Syntax?