Papers › Unsupervised Extractive Dialogue Summarization in Hyperdimensional Space

Unsupervised Extractive Dialogue Summarization in Hyperdimensional Space

16 May 2024arXiv:2405.09765archive 2025-07-28

Seongmin Park, Kyungho Kim, Jaejin Seo, Jihwa Lee

We present HyperSum, an extractive summarization framework that captures both the efficiency of traditional lexical summarization and the accuracy of contemporary neural approaches. HyperSum exploits the pseudo-orthogonality that emerges when randomly initializing vectors at extremely high dimensions ("blessing of dimensionality") to construct representative and efficient sentence embeddings. Simply clustering the obtained embeddings and extracting their medoids yields competitive summaries. HyperSum often outperforms state-of-the-art summarizers -- in terms of both summary accuracy and faithfulness -- while being 10 to 100 times faster. We open-source HyperSum as a strong baseline for unsupervised extractive summarization.

PaperPDFCode

Code

seongminp/hyperseg officialmentioned in papermentioned on GitHubpytorch report
seongminp/hdseg mentioned 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

ClusteringExtractive SummarizationSentenceSentence EmbeddingsUnsupervised Extractive Summarization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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