Towards Identifying Alternative-Lexicalization Signals of Discourse Relations

René Knaebel, Manfred Stede


Abstract
The task of shallow discourse parsing in the Penn Discourse Treebank (PDTB) framework has traditionally been restricted to identifying those relations that are signaled by a discourse connective (“explicit”) and those that have no signal at all (“implicit”). The third type, the more flexible group of “AltLex” realizations has been neglected because of its small amount of occurrences in the PDTB2 corpus. Their number has grown significantly in the recent PDTB3, and in this paper, we present the first approaches for recognizing these “alternative lexicalizations”. We compare the performance of a pattern-based approach and a sequence labeling model, add an experiment on the pre-classification of candidate sentences, and provide an initial qualitative analysis of the error cases made by both models.
Anthology ID:
2022.coling-1.70
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
837–850
Language:
URL:
https://aclanthology.org/2022.coling-1.70
DOI:
Bibkey:
Cite (ACL):
René Knaebel and Manfred Stede. 2022. Towards Identifying Alternative-Lexicalization Signals of Discourse Relations. In Proceedings of the 29th International Conference on Computational Linguistics, pages 837–850, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Towards Identifying Alternative-Lexicalization Signals of Discourse Relations (Knaebel & Stede, COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.70.pdf