Recurrent Neural Network Grammars

Chris Dyer, Adhiguna Kuncoro, Miguel Ballesteros, Noah A. Smith
2/25/2016
cs.CLcs.NE

Official code: clab/rnng (189 stars, last commit 2018-05-17).

Abstract

We introduce recurrent neural network grammars, probabilistic models of sentences with explicit phrase structure. We explain efficient inference procedures that allow application to both parsing and language modeling. Experiments show that they provide better parsing in English than any single previously published supervised generative model and better language modeling than state-of-the-art sequential RNNs in English and Chinese.

View on arXivView PDF

Code Implementations(1)

clab/rnngOfficial100%

Recurrent neural network grammars

18946C++, CudaApr 6, 20168 years ago

Similar Papers

Enhanced LSTM for Natural Language Inference

85% match1 repo2672016

Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation

84% match1 repo152016

An Overview on Language Models: Recent Developments and Outlook

83% match2023

Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State

83% match1 repo172019

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

83% match1 repo8922015

Hidden Schema Networks

82% match2022

Cite this paper

@article{dyer2016recurrent,
  title  = {Recurrent Neural Network Grammars},
  author = {Chris Dyer and Adhiguna Kuncoro and Miguel Ballesteros and Noah A. Smith},
  year   = {2016},
  eprint = {1602.07776},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1602.07776}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1602.07776.svg)](https://codeofpaper.com/paper/1602.07776)

Discussion