Papers › Top-down Discourse Parsing via Sequence Labelling
Top-down Discourse Parsing via Sequence Labelling
Fajri Koto, Jey Han Lau, Timothy Baldwin
We introduce a top-down approach to discourse parsing that is conceptually simpler than its predecessors (Kobayashi et al., 2020; Zhang et al., 2020). By framing the task as a sequence labelling problem where the goal is to iteratively segment a document into individual discourse units, we are able to eliminate the decoder and reduce the search space for splitting points. We explore both traditional recurrent models and modern pre-trained transformer models for the task, and additionally introduce a novel dynamic oracle for top-down parsing. Based on the Full metric, our proposed LSTM model sets a new state-of-the-art for RST parsing.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Discourse Parsing | RST-DT | LSTM Dynamic | Standard Parseval (Full) | 50.3 | #16 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | LSTM Dynamic | Standard Parseval (Nuclearity) | 62.3 | #16 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | LSTM Dynamic | Standard Parseval (Relation) | 51.5 | #16 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | LSTM Dynamic | Standard Parseval (Span) | 73.1 | #16 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | LSTM Static | Standard Parseval (Full) | 49.4 | #18 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | LSTM Static | Standard Parseval (Nuclearity) | 61.7 | #18 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | LSTM Static | Standard Parseval (Relation) | 50.5 | #18 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | LSTM Static | Standard Parseval (Span) | 72.7 | #18 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | Transformer (dynamic) | Standard Parseval (Full) | 49.2 | #19 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | Transformer (dynamic) | Standard Parseval (Nuclearity) | 60.1 | #19 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | Transformer (dynamic) | Standard Parseval (Span) | 70.2 | #19 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | Transformer (static) | Standard Parseval (Full) | 49.0 | #20 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | Transformer (static) | Standard Parseval (Nuclearity) | 59.9 | #20 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | Transformer (static) | Standard Parseval (Relation) | 50.6 | #20 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | Transformer (static) | Standard Parseval (Span) | 70.6 | #20 of 40 | 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.
Methods
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