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

05/14/2019

∙

by   Xiang Lin, et al.

∙

0

∙

share

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 F_1 score of 95.4, and our parser achieves an F_1 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 F_1).