Abstract
This paper describes our contribution to the PragTag-2023 Shared Task. We describe and compare different approaches based on sentence classification, sentence similarity, and sequence tagging. We find that a BERT-based sentence labeling approach integrating positional information outperforms both sequence tagging and SBERT-based sentence classification. We further provide analyses highlighting the potential of combining different approaches.- Anthology ID:
- 2023.argmining-1.22
- Volume:
- Proceedings of the 10th Workshop on Argument Mining
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Milad Alshomary, Chung-Chi Chen, Smaranda Muresan, Joonsuk Park, Julia Romberg
- Venues:
- ArgMining | WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 197–201
- Language:
- URL:
- https://aclanthology.org/2023.argmining-1.22
- DOI:
- 10.18653/v1/2023.argmining-1.22
- Cite (ACL):
- Yuning Ding, Marie Bexte, and Andrea Horbach. 2023. CATALPA_EduNLP at PragTag-2023. In Proceedings of the 10th Workshop on Argument Mining, pages 197–201, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- CATALPA_EduNLP at PragTag-2023 (Ding et al., ArgMining-WS 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.argmining-1.22.pdf