CLMay 23, 2024

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

arXiv:2405.14470v126 citationsh-index: 11Has CodeACL
Originality Synthesis-oriented
AI Analysis

This work addresses the challenge of improving multi-document summarization for researchers and practitioners by providing insights into summary composition, though it appears incremental as it applies an existing decomposition method to this domain.

The paper tackled the problem of understanding what makes high-quality multi-document summaries by analyzing human-written ones using partial information decomposition to break down mutual information into components like union and redundancy. The result showed a direct dependency between the number of source documents and their contribution to the summary.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes