Word-Context Character Embeddings for Chinese Word Segmentation
Hao Zhou, Zhenting Yu, Yue Zhang, Shujian Huang, Xinyu Dai, Jiajun Chen
Abstract
Neural parsers have benefited from automatically labeled data via dependency-context word embeddings. We investigate training character embeddings on a word-based context in a similar way, showing that the simple method improves state-of-the-art neural word segmentation models significantly, beating tri-training baselines for leveraging auto-segmented data.- Anthology ID:
- D17-1079
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 760–766
- Language:
- URL:
- https://aclanthology.org/D17-1079
- DOI:
- 10.18653/v1/D17-1079
- Cite (ACL):
- Hao Zhou, Zhenting Yu, Yue Zhang, Shujian Huang, Xinyu Dai, and Jiajun Chen. 2017. Word-Context Character Embeddings for Chinese Word Segmentation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 760–766, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Word-Context Character Embeddings for Chinese Word Segmentation (Zhou et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/D17-1079.pdf