ACL 2024findings0 citations
Which Information Matters? Dissecting Human-written Multi-document Summaries with Partial Information Decomposition
Laura Mascarell, Yan LHomme, Majed El Helou
Abstract
Understanding the nature of high-quality summaries is crucial to further improve the performance 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 information. Our empirical analysis on different MDS datasets shows that there is a direct dependency between the number of sources and their contribution to the summary.
BibTeX
@inproceedings{mascarell-etal-2024-information,
title = "Which Information Matters? Dissecting Human-written Multi-document Summaries with Partial Information Decomposition",
author = "Mascarell, Laura and
LHomme, Yan and
El Helou, Majed",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.316/",
doi = "10.18653/v1/2024.findings-acl.316",
pages = "5333--5338"
}