Pith. sign in

REVIEW 1 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1905.05682 v2 pith:NH5PYDMT submitted 2019-05-14 cs.CL cs.AI

Xiang Lin , Shafiq Joty , Prathyusha Jwalapuram , M Saiful Bari This is my paper · ORCID
classification cs.CLcs.AI
keywords discourseframeworkparsersegmenterscoresentence-levelaccordanceachieves
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
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 $F_1$).

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Hierarchical Pointer Net Parsing

    cs.CL 2019-08 conditional novelty 6.0 of 10

    A hierarchical pointer-network decoder that conditions on parent and sibling states improves discourse parsing relation F1 to 82.77 and gives marginal dependency parsing gains.

Pith tools