A Weakly-Supervised Learning Approach to the Identification of “Alternative Lexicalizations” in Shallow Discourse Parsing

René Knaebel


Abstract
Recently, the identification of free connective phrases as signals for discourse relations has received new attention with the introduction of statistical models for their automatic extraction. The limited amount of annotations makes it still challenging to develop well-performing models. In our work, we want to overcome this limitation with semi-supervised learning from unlabeled news texts. We implement a self-supervised sequence labeling approach and filter its predictions by a second model trained to disambiguate signal candidates. With our novel model design, we report state-of-the-art results and in addition, achieve an average improvement of about 5% for both exactly and partially matched alternativelylexicalized discourse signals due to weak supervision.
Anthology ID:
2023.codi-1.8
Volume:
Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Michael Strube, Chloe Braud, Christian Hardmeier, Junyi Jessy Li, Sharid Loaiciga, Amir Zeldes
Venue:
CODI
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
61–69
Language:
URL:
https://aclanthology.org/2023.codi-1.8
DOI:
10.18653/v1/2023.codi-1.8
Bibkey:
Cite (ACL):
René Knaebel. 2023. A Weakly-Supervised Learning Approach to the Identification of “Alternative Lexicalizations” in Shallow Discourse Parsing. In Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023), pages 61–69, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
A Weakly-Supervised Learning Approach to the Identification of “Alternative Lexicalizations” in Shallow Discourse Parsing (Knaebel, CODI 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.codi-1.8.pdf