A Unified Linear-Time Framework for Sentence-Level Discourse Parsing

Xiang Lin, Shafiq Joty, Prathyusha Jwalapuram, M Saiful Bari


Abstract
We propose an efficient neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory (RST). Our framework comprises a discourse segmenter to identify the elementary discourse units (EDU) in a text, and a discourse parser that constructs a discourse tree in a top-down fashion. Both the segmenter and the parser are based on Pointer Networks and operate in linear time. Our segmenter yields an F1 score of 95.4%, and our parser achieves an F1 score of 81.7% on the aggregated labeled (relation) metric, surpassing previous approaches by a good margin and approaching human agreement on both tasks (98.3 and 83.0 F1).
Anthology ID:
P19-1410
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4190–4200
Language:
URL:
https://aclanthology.org/P19-1410
DOI:
10.18653/v1/P19-1410
Bibkey:
Cite (ACL):
Xiang Lin, Shafiq Joty, Prathyusha Jwalapuram, and M Saiful Bari. 2019. A Unified Linear-Time Framework for Sentence-Level Discourse Parsing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4190–4200, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
A Unified Linear-Time Framework for Sentence-Level Discourse Parsing (Lin et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1410.pdf
Supplementary:
 P19-1410.Supplementary.pdf
Video:
 https://aclanthology.org/P19-1410.mp4
Code
 additional community code