Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading

Feng Jiang, Xiaomin Chu, Peifeng Li, Fang Kong, Qiaoming Zhu


Abstract
Discourse structure tree construction is the fundamental task of discourse parsing and most previous work focused on English. Due to the cultural and linguistic differences, existing successful methods on English discourse parsing cannot be transformed into Chinese directly, especially in paragraph level suffering from longer discourse units and fewer explicit connectives. To alleviate the above issues, we propose two reading modes, i.e., the global backward reading and the local reverse reading, to construct Chinese paragraph level discourse trees. The former processes discourse units from the end to the beginning in a document to utilize the left-branching bias of discourse structure in Chinese, while the latter reverses the position of paragraphs in a discourse unit to enhance the differentiation of coherence between adjacent discourse units. The experimental results on Chinese MCDTB demonstrate that our model outperforms all strong baselines.
Anthology ID:
2020.coling-main.506
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5749–5759
Language:
URL:
https://aclanthology.org/2020.coling-main.506
DOI:
10.18653/v1/2020.coling-main.506
Bibkey:
Cite (ACL):
Feng Jiang, Xiaomin Chu, Peifeng Li, Fang Kong, and Qiaoming Zhu. 2020. Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5749–5759, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading (Jiang et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.506.pdf