Read Top News First: A Document Reordering Approach for Multi-Document News Summarization
Computation and Language
2022-03-22 v1
Abstract
A common method for extractive multi-document news summarization is to re-formulate it as a single-document summarization problem by concatenating all documents as a single meta-document. However, this method neglects the relative importance of documents. We propose a simple approach to reorder the documents according to their relative importance before concatenating and summarizing them. The reordering makes the salient content easier to learn by the summarization model. Experiments show that our approach outperforms previous state-of-the-art methods with more complex architectures.
Cite
@article{arxiv.2203.10254,
title = {Read Top News First: A Document Reordering Approach for Multi-Document News Summarization},
author = {Chao Zhao and Tenghao Huang and Somnath Basu Roy Chowdhury and Muthu Kumar Chandrasekaran and Kathleen McKeown and Snigdha Chaturvedi},
journal= {arXiv preprint arXiv:2203.10254},
year = {2022}
}
Comments
Accepted at Findings of ACL 2022