The centroid method is a simple approach for extractive multi-document summarization and many improvements to its pipeline have been proposed. We further refine it by adding a beam search process to the sentence selection and also a centroid estimation attention model that leads to improved results. We demonstrate this in several multi-document summarization datasets, including in a multilingual scenario.
@article{arxiv.2311.17771,
title = {Supervising the Centroid Baseline for Extractive Multi-Document Summarization},
author = {Simão Gonçalves and Gonçalo Correia and Diogo Pernes and Afonso Mendes},
journal= {arXiv preprint arXiv:2311.17771},
year = {2023}
}
Comments
Accepted at "The 4th New Frontiers in Summarization (with LLMs) Workshop"