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
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Sara Goggi, Marko Grobelnik, Bente Maegaard, Joseph Mariani, Helene Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
1034–1038
Language:
URL:
https://aclanthology.org/L16-1164
DOI:
Bibkey:
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)
Copy Citation:
PDF:
https://aclanthology.org/L16-1164.pdf