English

Chinese NER Using Lattice LSTM

Computation and Language 2018-07-06 v4

Abstract

We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon. Compared with character-based methods, our model explicitly leverages word and word sequence information. Compared with word-based methods, lattice LSTM does not suffer from segmentation errors. Gated recurrent cells allow our model to choose the most relevant characters and words from a sentence for better NER results. Experiments on various datasets show that lattice LSTM outperforms both word-based and character-based LSTM baselines, achieving the best results.

Keywords

Cite

@article{arxiv.1805.02023,
  title  = {Chinese NER Using Lattice LSTM},
  author = {Yue Zhang and Jie Yang},
  journal= {arXiv preprint arXiv:1805.02023},
  year   = {2018}
}

Comments

Accepted at ACL 2018 as Long paper

R2 v1 2026-06-23T01:45:52.500Z