Unsupervised Extractive Dialogue Summarization in Hyperdimensional Space

Seongmin Park, Kyungho Kim, Jaejin Seo, Jihwa Lee

2024-05-16Unsupervised Extractive Summarization Sentence Embeddings Clustering Extractive Summarization

Abstract

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.

Related Papers

From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment2025-07-20 Tri-Learn Graph Fusion Network for Attributed Graph Clustering2025-07-18 SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts2025-07-17 Ranking Vectors Clustering: Theory and Applications2025-07-16 Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework2025-07-11 GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning2025-07-09 Consistency and Inconsistency in $K$-Means Clustering2025-07-08 MC-INR: Efficient Encoding of Multivariate Scientific Simulation Data using Meta-Learning and Clustered Implicit Neural Representations2025-07-03