Papers › A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues

A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues

1 Aug 2021Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence 2021 8archive 2025-07-28

An-Hui Wang, Linfeng Song, Hui Jiang, Shaopeng Lai, Junfeng Yao, Min Zhang, Jinsong Su

Conversational discourse structures aim to describe how a dialogue is organised, thus they are helpful for dialogue understanding and response generation. This paper focuses on predicting discourse dependency structures for multi-party dialogues. Previous work adopts incremental methods that take the features from the already predicted discourse relations to help generate the next one. Although the inter-correlations among predictions are considered, we find that the error propagation is also very serious and hurts the overall performance. To alleviate error propagation, we propose a Structure Self-Aware (SSA) model, which adopts a novel edge-centric Graph Neural Network (GNN) to update the information between each Elementary Discourse Unit (EDU) pair layer by layer, so that expressive representations can be learned without historical predictions. In addition, we take auxiliary training signals (e.g. structure distillation) for better representation learning. Our model achieves the new state-of-the-art performances on two conversational discourse parsing benchmarks, largely outperforming the previous methods.

PaperPDFCode

Code

DeepLearnXMU/Structure-Self-Aware officialmentioned in paperpytorch 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

Dialogue UnderstandingDiscourse ParsingGraph Neural NetworkRepresentation LearningResponse Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Discourse Parsing Molweni Struct-Aware Link & Rel F1 58.4 #5 of 7 Archive leaderboard report
Discourse Parsing Molweni Struct-Aware Link F1 81.6 #5 of 7 Archive leaderboard report
Discourse Parsing STAC Struct-Aware Link & Rel F1 57.3 #3 of 7 Archive leaderboard report
Discourse Parsing STAC Struct-Aware Link F1 73.4 #3 of 7 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

Graph Neural Network

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