Abstract
We present neural network-based joint models for Chinese word segmentation, POS tagging and dependency parsing. Our models are the first neural approaches for fully joint Chinese analysis that is known to prevent the error propagation problem of pipeline models. Although word embeddings play a key role in dependency parsing, they cannot be applied directly to the joint task in the previous work. To address this problem, we propose embeddings of character strings, in addition to words. Experiments show that our models outperform existing systems in Chinese word segmentation and POS tagging, and perform preferable accuracies in dependency parsing. We also explore bi-LSTM models with fewer features.- Anthology ID:
- P17-1111
- Volume:
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2017
- Address:
- Vancouver, Canada
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1204–1214
- Language:
- URL:
- https://aclanthology.org/P17-1111
- DOI:
- 10.18653/v1/P17-1111
- Cite (ACL):
- Shuhei Kurita, Daisuke Kawahara, and Sadao Kurohashi. 2017. Neural Joint Model for Transition-based Chinese Syntactic Analysis. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1204–1214, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Neural Joint Model for Transition-based Chinese Syntactic Analysis (Kurita et al., ACL 2017)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/P17-1111.pdf