papers AI Learner
The Github is limit! Click to go to the new site.

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

2019-05-14
Xiang Lin, Shafiq Joty, Prathyusha Jwalapuram, 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 $F_1$ 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 $F_1$).

Abstract (translated by Google)
URL

https://arxiv.org/abs/1905.05682

PDF

https://arxiv.org/pdf/1905.05682


Similar Posts

Comments