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

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

14 May 2019ACL 2019 7arXiv:1905.05682archive 2025-07-28

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

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).

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ntunlpsg/UnifiedParser_RST mentioned on GitHubpytorch report
shawnlimn/UnifiedParser_RST mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Discourse ParsingSentence

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections