English

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

Computation and Language 2015-08-12 v2

Abstract

We present extensions to a continuous-state dependency parsing method that makes it applicable to morphologically rich languages. Starting with a high-performance transition-based parser that uses long short-term memory (LSTM) recurrent neural networks to learn representations of the parser state, we replace lookup-based word representations with representations constructed from the orthographic representations of the words, also using LSTMs. This allows statistical sharing across word forms that are similar on the surface. Experiments for morphologically rich languages show that the parsing model benefits from incorporating the character-based encodings of words.

Keywords

Cite

@article{arxiv.1508.00657,
  title  = {Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs},
  author = {Miguel Ballesteros and Chris Dyer and Noah A. Smith},
  journal= {arXiv preprint arXiv:1508.00657},
  year   = {2015}
}

Comments

In Proceedings of EMNLP 2015

R2 v1 2026-06-22T10:25:42.614Z