W-RST: Towards a Weighted RST-style Discourse Framework

Patrick Huber, Wen Xiao, Giuseppe Carenini


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
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
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp-22-attachments/2021.acl-long.302.pdf
Video:
 https://preview.aclanthology.org/emnlp-22-attachments/2021.acl-long.302.mp4
Data
CNN/Daily Mail