Papers › Multi-view and multi-task training of RST discourse parsers
Multi-view and multi-task training of RST discourse parsers
Chlo{\'e} Braud, Barbara Plank, Anders S{\o}gaard
We experiment with different ways of training LSTM networks to predict RST discourse trees. The main challenge for RST discourse parsing is the limited amounts of training data. We combat this by regularizing our models using task supervision from related tasks as well as alternative views on discourse structures. We show that a simple LSTM sequential discourse parser takes advantage of this multi-view and multi-task framework with 12-15{\%} error reductions over our baseline (depending on the metric) and results that rival more complex state-of-the-art parsers.
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 Sequential Discourse Parser (Braud et al., 2016) | RST-Parseval (Full) | 47.5* | #40 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | LSTM Sequential Discourse Parser (Braud et al., 2016) | RST-Parseval (Nuclearity) | 63.6* | #40 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | LSTM Sequential Discourse Parser (Braud et al., 2016) | RST-Parseval (Relation) | 47.7* | #40 of 40 | Archive leaderboard | report |
| Discourse Parsing | RST-DT | LSTM Sequential Discourse Parser (Braud et al., 2016) | RST-Parseval (Span) | 79.7* | #40 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