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

ACL 2019

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

Jan 31, 2021
|
22 views
|
|
Code
Details
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). Authors: Xiang Lin, Shafiq Joty, Prathyusha Jwalapuram, M Saiful Bari (Nanyang Technological University, Salesforce Research Asia)

Comments
loading...