English

Syntactically Informed Text Compression with Recurrent Neural Networks

Machine Learning 2016-08-30 v2 Computation and Language Information Theory math.IT

Abstract

We present a self-contained system for constructing natural language models for use in text compression. Our system improves upon previous neural network based models by utilizing recent advances in syntactic parsing -- Google's SyntaxNet -- to augment character-level recurrent neural networks. RNNs have proven exceptional in modeling sequence data such as text, as their architecture allows for modeling of long-term contextual information.

Keywords

Cite

@article{arxiv.1608.02893,
  title  = {Syntactically Informed Text Compression with Recurrent Neural Networks},
  author = {David Cox},
  journal= {arXiv preprint arXiv:1608.02893},
  year   = {2016}
}

Comments

12 pages, 3 figures

R2 v1 2026-06-22T15:16:07.639Z