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.
CITATION STYLE
Zhang, Y., & Yang, J. (2018). Chinese nEr using lattice LSTM. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (Vol. 1, pp. 1554–1564). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p18-1144
Mendeley helps you to discover research relevant for your work.