Chinese Discourse Parsing: Model and Evaluation

Lin Chuan-An, Shyh-Shiun Hung, Hen-Hsen Huang, Hsin-Hsi Chen


Abstract
Chinese discourse parsing, which aims to identify the hierarchical relationships of Chinese elementary discourse units, has not yet a consistent evaluation metric. Although Parseval is commonly used, variations of evaluation differ from three aspects: micro vs. macro F1 scores, binary vs. multiway ground truth, and left-heavy vs. right-heavy binarization. In this paper, we first propose a neural network model that unifies a pre-trained transformer and CKY-like algorithm, and then compare it with the previous models with different evaluation scenarios. The experimental results show that our model outperforms the previous systems. We conclude that (1) the pre-trained context embedding provides effective solutions to deal with implicit semantics in Chinese texts, and (2) using multiway ground truth is helpful since different binarization approaches lead to significant differences in performance.
Anthology ID:
2020.lrec-1.128
Volume:
Proceedings of the 12th Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
1019–1024
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.128
DOI:
Bibkey:
Cite (ACL):
Lin Chuan-An, Shyh-Shiun Hung, Hen-Hsen Huang, and Hsin-Hsi Chen. 2020. Chinese Discourse Parsing: Model and Evaluation. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 1019–1024, Marseille, France. European Language Resources Association.
Cite (Informal):
Chinese Discourse Parsing: Model and Evaluation (Chuan-An et al., LREC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lrec-1.128.pdf