</> Code with Papers by Syntology

Papers › Neural RST-based Evaluation of Discourse Coherence

Neural RST-based Evaluation of Discourse Coherence

30 Sep 2020Asian Chapter of the Association for Computational Linguistics 2020arXiv:2009.14463archive 2025-07-28

Grigorii Guz, Peyman Bateni, Darius Muglich, Giuseppe Carenini

This paper evaluates the utility of Rhetorical Structure Theory (RST) trees and relations in discourse coherence evaluation. We show that incorporating silver-standard RST features can increase accuracy when classifying coherence. We demonstrate this through our tree-recursive neural model, namely RST-Recursive, which takes advantage of the text's RST features produced by a state of the art RST parser. We evaluate our approach on the Grammarly Corpus for Discourse Coherence (GCDC) and show that when ensembled with the current state of the art, we can achieve the new state of the art accuracy on this benchmark. Furthermore, when deployed alone, RST-Recursive achieves competitive accuracy while having 62% fewer parameters.

PaperPDFConference PDFCode

Code

grig-guz/coherence-rst officialmentioned in papermentioned 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

Coherence EvaluationDiscourse ParsingDocument ClassificationNatural Language UnderstandingText Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Coherence Evaluation GCDC + RST - Accuracy RST-Ensemble Accuracy 55.39 #2 of 4 Archive leaderboard report
Coherence Evaluation GCDC + RST - Accuracy RST-Recursive Accuracy 53.04 #4 of 4 Archive leaderboard report
Coherence Evaluation GCDC + RST - F1 RST-Ensemble Average F1 46.98 #1 of 3 Archive leaderboard report
Coherence Evaluation GCDC + RST - F1 RST-Recursive Average F1 44.30 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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