State-of-the-art Chinese Word Segmentation with Bi-LSTMs

Ji Ma, Kuzman Ganchev, David Weiss


Abstract
A wide variety of neural-network architectures have been proposed for the task of Chinese word segmentation. Surprisingly, we find that a bidirectional LSTM model, when combined with standard deep learning techniques and best practices, can achieve better accuracy on many of the popular datasets as compared to models based on more complex neuralnetwork architectures. Furthermore, our error analysis shows that out-of-vocabulary words remain challenging for neural-network models, and many of the remaining errors are unlikely to be fixed through architecture changes. Instead, more effort should be made on exploring resources for further improvement.
Anthology ID:
D18-1529
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4902–4908
Language:
URL:
https://aclanthology.org/D18-1529
DOI:
10.18653/v1/D18-1529
Bibkey:
Cite (ACL):
Ji Ma, Kuzman Ganchev, and David Weiss. 2018. State-of-the-art Chinese Word Segmentation with Bi-LSTMs. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4902–4908, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
State-of-the-art Chinese Word Segmentation with Bi-LSTMs (Ma et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1529.pdf