@inproceedings{yang-etal-2019-subword, title = "Subword Encoding in Lattice {LSTM} for {C}hinese Word Segmentation", author = "Yang, Jie and Zhang, Yue and Liang, Shuailong", booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)", month = jun, year = "2019", address = "Minneapolis, Minnesota", publisher = "Association for Computational Linguistics", url = "https://www.aclweb.org/anthology/N19-1278", pages = "2720--2725", abstract = "We investigate subword information for Chinese word segmentation, by integrating sub word embeddings trained using byte-pair encoding into a Lattice LSTM (LaLSTM) network over a character sequence. Experiments on standard benchmark show that subword information brings significant gains over strong character-based segmentation models. To our knowledge, this is the first research on the effectiveness of subwords on neural word segmentation.", }