Abstract
Aiming for a better integration of data-driven and linguistically-inspired approaches, we explore whether RST Nuclearity, assigning a binary assessment of importance between text segments, can be replaced by automatically generated, real-valued scores, in what we call a Weighted-RST framework. In particular, we find that weighted discourse trees from auxiliary tasks can benefit key NLP downstream applications, compared to nuclearity-centered approaches. We further show that real-valued importance distributions partially and interestingly align with the assessment and uncertainty of human annotators.- Anthology ID:
- 2021.acl-long.302
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3908–3918
- Language:
- URL:
- https://aclanthology.org/2021.acl-long.302
- DOI:
- 10.18653/v1/2021.acl-long.302
- Cite (ACL):
- Patrick Huber, Wen Xiao, and Giuseppe Carenini. 2021. W-RST: Towards a Weighted RST-style Discourse Framework. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3908–3918, Online. Association for Computational Linguistics.
- Cite (Informal):
- W-RST: Towards a Weighted RST-style Discourse Framework (Huber et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2021.acl-long.302.pdf
- Data
- CNN/Daily Mail