Which Information Matters? Dissecting Human-written Multi-document Summaries with Partial Information Decomposition


Date

2024-08

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Understanding the nature of high-quality sum maries is crucial to further improve the perfor mance of multi-document summarization. We propose an approach to characterize human written summaries using partial information decomposition, which decomposes the mutual information provided by all source documents into union, redundancy, synergy, and unique in formation. Our empirical analysis on different MDS datasets shows that there is a direct de pendency between the number of sources and their contribution to the summary.

Publication status

published

Book title

Findings of the Association for Computational Linguistics: ACL 2024

Journal / series

Volume

Pages / Article No.

5333 - 5338

Publisher

Association for Computational Linguistics

Event

62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

02154 - Media Technology Center (MTC) / Media Technology Center (MTC)

Notes

Funding

Related publications and datasets