Papers › Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization

Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization

2 Sep 2022COLING 2022 10arXiv:2209.00930archive 2025-07-28

Seungone Kim, Se June Joo, Hyungjoo Chae, Chaehyeong Kim, Seung-won Hwang, Jinyoung Yeo

In this paper, we propose to leverage the unique characteristics of dialogues sharing commonsense knowledge across participants, to resolve the difficulties in summarizing them. We present SICK, a framework that uses commonsense inferences as additional context. Compared to previous work that solely relies on the input dialogue, SICK uses an external knowledge model to generate a rich set of commonsense inferences and selects the most probable one with a similarity-based selection method. Built upon SICK, SICK++ utilizes commonsense as supervision, where the task of generating commonsense inferences is added upon summarizing the dialogue in a multi-task learning setting. Experimental results show that with injected commonsense knowledge, our framework generates more informative and consistent summaries than existing methods.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

SeungoneKim/SICK_Summarization officialmentioned on GitHubpytorch 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

Abstractive Dialogue SummarizationMulti-Task LearningText Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Summarization DialogSum SICK BertScore 71.30 #4 of 4 Archive leaderboard report
Text Summarization DialogSum SICK Rouge1 46.26 #4 of 4 Archive leaderboard report
Text Summarization DialogSum SICK Rouge2 20.95 #4 of 4 Archive leaderboard report
Text Summarization DialogSum SICK RougeL 41.05 #4 of 4 Archive leaderboard report
Text Summarization SAMSum SICK BertScoreF1 71.92 #6 of 12 Archive leaderboard report
Text Summarization SAMSum SICK ROUGE-1 53.73 #6 of 12 Archive leaderboard report
Text Summarization SAMSum SICK ROUGE-2 28.81 #6 of 12 Archive leaderboard report
Text Summarization SAMSum SICK ROUGE-L 49.5 #6 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.

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