# Unsupervised Extractive Dialogue Summarization in Hyperdimensional Space

arXiv: https://arxiv.org/abs/2405.09765 · HTML: https://mlsanity.com/paper/2405.09765/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 16 May 2024.

## Builds on (most cited first, 7 of 7)

- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges](https://mlsanity.com/paper/2112.15424/) (2021)
- [Blessing of dimensionality: mathematical foundations of the statistical physics of data](https://mlsanity.com/paper/1801.03421/) (2018)
- [A Survey on Dialogue Summarization: Recent Advances and New Frontiers](https://mlsanity.com/paper/2107.03175/) (2021)
- [Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization](https://mlsanity.com/paper/2209.03549/) (2022)
- [StreamHover: Livestream Transcript Summarization and Annotation](https://mlsanity.com/paper/2109.05160/) (2021)
- [OTExtSum: Extractive Text Summarisation with Optimal Transport](https://mlsanity.com/paper/2204.10086/) (2022)

## Abstract (arXiv)

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.