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.
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