Abstract
HITS participated in the Discourse Segmentation (DS, Task 1) and Connective Detection (CD, Task 2) tasks at the DISRPT 2023. Task 1 focuses on segmenting the text into discourse units, while Task 2 aims to detect the discourse connectives. We deployed a framework based on different pre-trained models according to the target language for these two tasks.HITS also participated in the Relation Classification track (Task 3). The main task was recognizing the discourse relation between text spans from different languages. We designed a joint model for languages with a small corpus while separate models for large corpora. The adversarial training strategy is applied to enhance the robustness of relation classifiers.- Anthology ID:
- 2023.disrpt-1.4
- Volume:
- Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Chloé Braud, Yang Janet Liu, Eleni Metheniti, Philippe Muller, Laura Rivière, Attapol Rutherford, Amir Zeldes
- Venue:
- DISRPT
- SIG:
- Publisher:
- The Association for Computational Linguistics
- Note:
- Pages:
- 43–49
- Language:
- URL:
- https://aclanthology.org/2023.disrpt-1.4
- DOI:
- 10.18653/v1/2023.disrpt-1.4
- Cite (ACL):
- Wei Liu, Yi Fan, and Michael Strube. 2023. HITS at DISRPT 2023: Discourse Segmentation, Connective Detection, and Relation Classification. In Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023), pages 43–49, Toronto, Canada. The Association for Computational Linguistics.
- Cite (Informal):
- HITS at DISRPT 2023: Discourse Segmentation, Connective Detection, and Relation Classification (Liu et al., DISRPT 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.disrpt-1.4.pdf