Fine-Grained Chinese Discourse Relation Labelling
Huan-Yuan Chen, Wan-Shan Liao, Hen-Hsen Huang, Hsin-Hsi Chen
Abstract
This paper explores several aspects together for a fine-grained Chinese discourse analysis. We deal with the issues of ambiguous discourse markers, ambiguous marker linkings, and more than one discourse marker. A universal feature representation is proposed. The pair-once postulation, cross-discourse-unit-first rule and word-pair-marker-first rule select a set of discourse markers from ambiguous linkings. Marker-Sum feature considers total contribution of markers and Marker-Preference feature captures the probability distribution of discourse functions of a representative marker by using preference rule. The HIT Chinese discourse relation treebank (HIT-CDTB) is used to evaluate the proposed models. The 25-way classifier achieves 0.57 micro-averaged F-score.- Anthology ID:
- L16-1164
- Volume:
- Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)
- Month:
- May
- Year:
- 2016
- Address:
- Portorož, Slovenia
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association (ELRA)
- Note:
- Pages:
- 1034–1038
- Language:
- URL:
- https://aclanthology.org/L16-1164
- DOI:
- Cite (ACL):
- Huan-Yuan Chen, Wan-Shan Liao, Hen-Hsen Huang, and Hsin-Hsi Chen. 2016. Fine-Grained Chinese Discourse Relation Labelling. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1034–1038, Portorož, Slovenia. European Language Resources Association (ELRA).
- Cite (Informal):
- Fine-Grained Chinese Discourse Relation Labelling (Chen et al., LREC 2016)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/L16-1164.pdf