Papers › Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization
Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization
Junpeng Liu, Yanyan Zou, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Caixia Yuan, Xiaojie Wang
Unlike well-structured text, such as news reports and encyclopedia articles, dialogue content often comes from two or more interlocutors, exchanging information with each other. In such a scenario, the topic of a conversation can vary upon progression and the key information for a certain topic is often scattered across multiple utterances of different speakers, which poses challenges to abstractly summarize dialogues. To capture the various topic information of a conversation and outline salient facts for the captured topics, this work proposes two topic-aware contrastive learning objectives, namely coherence detection and sub-summary generation objectives, which are expected to implicitly model the topic change and handle information scattering challenges for the dialogue summarization task. The proposed contrastive objectives are framed as auxiliary tasks for the primary dialogue summarization task, united via an alternative parameter updating strategy. Extensive experiments on benchmark datasets demonstrate that the proposed simple method significantly outperforms strong baselines and achieves new state-of-the-art performance. The code and trained models are publicly available via \href{https://github.com/Junpliu/ConDigSum}{https://github.com/Junpliu/ConDigSum}.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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 |
|---|---|---|---|---|---|---|---|
| Text Summarization | SAMSum | ConDigSum | BertScoreF1 | 54 | #5 of 12 | Archive leaderboard | report |
| Text Summarization | SAMSum | ConDigSum | ROUGE-1 | 54.3 | #5 of 12 | Archive leaderboard | report |
| Text Summarization | SAMSum | ConDigSum | ROUGE-2 | 29.3 | #5 of 12 | Archive leaderboard | report |
| Text Summarization | SAMSum | ConDigSum | ROUGE-L | 45.2 | #5 of 12 | Archive leaderboard | report |
| Text Summarization | SAMSum | BART-Large | BertScoreF1 | 52.1 | #8 of 12 | Archive leaderboard | report |
| Text Summarization | SAMSum | BART-Large | ROUGE-1 | 52.6 | #8 of 12 | Archive leaderboard | report |
| Text Summarization | SAMSum | BART-Large | ROUGE-2 | 27 | #8 of 12 | Archive leaderboard | report |
| Text Summarization | SAMSum | BART-Large | ROUGE-L | 42.1 | #8 of 12 | 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