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