Improving Sentence Similarity Estimation for Unsupervised Extractive Summarization

Shichao Sun, Ruifeng Yuan, Wenjie Li, Sujian Li

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Unsupervised extractive summarization aims to extract salient sentences from a document as the summary without labeled data. Recent literatures mostly research how to leverage sentence similarity to rank sentences in the order of salience. However, sentence similarity estimation using pre-trained language models mostly takes little account of document-level information and has a weak correlation with sentence salience ranking. In this paper, we proposed two novel strategies to improve sentence similarity estimation for unsupervised extractive summarization. We use contrastive learning to optimize a document-level objective that sentences from the same document are more similar than those from different documents. Moreover, we use mutual learning to enhance the relationship between sentence similarity estimation and sentence salience ranking, where an extra signal amplifier is used to refine the pivotal information. Experimental results demonstrate the effectiveness of our strategies.1

Original languageEnglish
Title of host publicationICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728163277
DOIs
Publication statusPublished - 2023
Event48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece
Duration: 4 Jun 202310 Jun 2023

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2023-June
ISSN (Print)1520-6149

Conference

Conference48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
Country/TerritoryGreece
CityRhodes Island
Period4/06/2310/06/23

Keywords

  • Contrastive Learning
  • Mutual Learning
  • Sentence Similarity
  • Unsupervised Extractive Summarization

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Improving Sentence Similarity Estimation for Unsupervised Extractive Summarization'. Together they form a unique fingerprint.

Cite this