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

arXiv: https://arxiv.org/abs/2405.14470 · HTML: https://mlsanity.com/paper/2405.14470/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 23 May 2024.

## Builds on (most cited first, 9 of 9)

- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [Generating Wikipedia by Summarizing Long Sequences](https://mlsanity.com/paper/1801.10198/) (2018)
- [A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal](https://mlsanity.com/paper/2005.10070/) (2020)
- [Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization](https://mlsanity.com/paper/1808.06218/) (2018)
- [Mutual Information and Diverse Decoding Improve Neural Machine Translation](https://mlsanity.com/paper/1601.00372/) (2016)
- [Unsupervised Extractive Summarization using Pointwise Mutual Information](https://mlsanity.com/paper/2102.06272/) (2021)
- [A Novel Approach to the Partial Information Decomposition](https://mlsanity.com/paper/1908.08642/) (2019)
- [TWAG: A Topic-Guided Wikipedia Abstract Generator](https://mlsanity.com/paper/2106.15135/) (2021)

## Abstract (arXiv)

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.