SumHiS: Extractive Summarization Exploiting Hidden Structure

TL;DR

SumHiS introduces a novel extractive summarization method leveraging hidden text structures, achieving state-of-the-art ROUGE-2 scores on CNN/DailyMail by interpreting text as aspects.

Contribution

The paper presents a new extractive summarization approach that exploits hidden clustering structures in text, improving summary accuracy over existing methods.

Findings

Outperforms previous methods on CNN/DailyMail with 10% higher ROUGE-2 score

Effectively interprets hidden text structures as aspects

Achieves state-of-the-art summarization results

Abstract

Extractive summarization is a task of highlighting the most important parts of the text. We introduce a new approach to extractive summarization task using hidden clustering structure of the text. Experimental results on CNN/DailyMail demonstrate that our approach generates more accurate summaries than both extractive and abstractive methods, achieving state-of-the-art results in terms of ROUGE-2 metric exceeding the previous approaches by 10%. Additionally, we show that hidden structure of the text could be interpreted as aspects.