# Multi-Document Summarization via Discriminative Summary Reranking

arXiv: https://arxiv.org/abs/1507.02062 · HTML: https://mlsanity.com/paper/1507.02062/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2015.

## Built on by (most cited first, 6 of 6)

- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [BRIO: Bringing Order to Abstractive Summarization](https://mlsanity.com/paper/2203.16804/) (2022)
- [SgSum: Transforming Multi-document Summarization into Sub-graph Selection](https://mlsanity.com/paper/2110.12645/) (2021)
- [Momentum Calibration for Text Generation](https://mlsanity.com/paper/2212.04257/) (2022)
- [A Mixed-Language Multi-Document News Summarization Dataset and a Graphs-Based Extract-Generate Model](https://mlsanity.com/paper/2410.09773/) (2024)
- [Guiding ChatGPT to Generate Salient Domain Summaries](https://mlsanity.com/paper/2406.01070/) (2024)

## Abstract (arXiv)

Existing multi-document summarization systems usually rely on a specific summarization model (i.e., a summarization method with a specific parameter setting) to extract summaries for different document sets with different topics. However, according to our quantitative analysis, none of the existing summarization models can always produce high-quality summaries for different document sets, and even a summarization model with good overall performance may produce low-quality summaries for some document sets. On the contrary, a baseline summarization model may produce high-quality summaries for some document sets. Based on the above observations, we treat the summaries produced by different summarization models as candidate summaries, and then explore discriminative reranking techniques to identify high-quality summaries from the candidates for difference document sets. We propose to extract a set of candidate summaries for each document set based on an ILP framework, and then leverage Ranking SVM for summary reranking. Various useful features have been developed for the reranking process, including word-level features, sentence-level features and summary-level features. Evaluation results on the benchmark DUC datasets validate the efficacy and robustness of our proposed approach.