SumHiS: extractive summarization exploiting hidden structure

P. A. Tikhonov^ab, A. O. Yanina^c, V. A. Malykh<sup>d

a</sup> Artificial Intelligence Research Institute
^b Skolkovo Institute of Science and Technology
^c Moscow Institute of Physics and Technology
^d ITMO University

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

Keywords: summarization, NLP.

DOI: 10.15514/ISPRAS-2025-37(3)-17