Papers › Bilingual Rhetorical Structure Parsing with Large Parallel Annotations

Bilingual Rhetorical Structure Parsing with Large Parallel Annotations

23 Sep 2024arXiv:2409.14969archive 2025-07-28

Elena Chistova

Discourse parsing is a crucial task in natural language processing that aims to reveal the higher-level relations in a text. Despite growing interest in cross-lingual discourse parsing, challenges persist due to limited parallel data and inconsistencies in the Rhetorical Structure Theory (RST) application across languages and corpora. To address this, we introduce a parallel Russian annotation for the large and diverse English GUM RST corpus. Leveraging recent advances, our end-to-end RST parser achieves state-of-the-art results on both English and Russian corpora. It demonstrates effectiveness in both monolingual and bilingual settings, successfully transferring even with limited second-language annotation. To the best of our knowledge, this work is the first to evaluate the potential of cross-lingual end-to-end RST parsing on a manually annotated parallel corpus.

PaperPDFCode

Code

tchewik/bilingualrsp officialpytorch 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 ParsingEnd-to-End RST Parsing

Datasets

Introduced by this paper, per the archive.

RRG

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Discourse Parsing RST-DT DMRST Standard Parseval (Full) 55.7 ± 0.3 #5 of 40 Archive leaderboard report
Discourse Parsing RST-DT DMRST Standard Parseval (Nuclearity) 68.0 ± 0.6 #5 of 40 Archive leaderboard report
Discourse Parsing RST-DT DMRST Standard Parseval (Relation) 57.3 ± 0.2 #5 of 40 Archive leaderboard report
Discourse Parsing RST-DT DMRST Standard Parseval (Span) 78.7 ± 0.4 #5 of 40 Archive leaderboard report
End-to-End RST Parsing RST-DT DMRST + ToNy + E-BiLSTM Standard Parseval (Full) 53.0 ± 0.7 #1 of 4 Archive leaderboard report
End-to-End RST Parsing RST-DT DMRST + ToNy + E-BiLSTM Standard Parseval (Nuclearity) 64.5 ± 0.8 #1 of 4 Archive leaderboard report
End-to-End RST Parsing RST-DT DMRST + ToNy + E-BiLSTM Standard Parseval (Relation) 54.5 ± 0.7 #1 of 4 Archive leaderboard report
End-to-End RST Parsing RST-DT DMRST + ToNy + E-BiLSTM Standard Parseval (Span) 74.8 ± 0.5 #1 of 4 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