TY - GEN
T1 - Improving Sentence Similarity Estimation for Unsupervised Extractive Summarization
AU - Sun, Shichao
AU - Yuan, Ruifeng
AU - Li, Wenjie
AU - Li, Sujian
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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
AB - 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
KW - Contrastive Learning
KW - Mutual Learning
KW - Sentence Similarity
KW - Unsupervised Extractive Summarization
UR - http://www.scopus.com/inward/record.url?scp=85177599574&partnerID=8YFLogxK
U2 - 10.1109/ICASSP49357.2023.10096137
DO - 10.1109/ICASSP49357.2023.10096137
M3 - Conference article published in proceeding or book
AN - SCOPUS:85177599574
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
BT - ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
Y2 - 4 June 2023 through 10 June 2023
ER -