Abstract
Implicit discourse relation recognition is a challenging task that involves identifying the sense or senses that hold between two adjacent spans of text, in the absense of an explicit connective between them. In both PDTB-2 (prasad et al., 2008) and PDTB-3 (Webber et al., 2019), discourse relational senses are organized into a three-level hierarchy ranging from four broad top-level senses, to more specific senses below them. Most previous work on implicitf discourse relation recognition have used the sense hierarchy simply to indicate what sense labels were available. Here we do more — incorporating the sense hierarchy into the recognition process itself and using it to select the negative examples used in contrastive learning. With no additional effort, the approach achieves state-of-the-art performance on the task. Our code is released inhttps://github.com/wanqiulong 0923/Contrastive_IDRR.- Anthology ID:
- 2022.emnlp-main.734
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 10704–10716
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.734
- DOI:
- 10.18653/v1/2022.emnlp-main.734
- Cite (ACL):
- Wanqiu Long and Bonnie Webber. 2022. Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10704–10716, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations (Long & Webber, EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2022.emnlp-main.734.pdf