@inproceedings{lin2004rouge,
author = {Lin, Chin-Yew},
title = {ROUGE: a Package for Automatic Evaluation of Summaries},
booktitle = {Workshop on Text Summarization Branches Out, Post-Conference Workshop of ACL 2004, Barcelona, Spain},
year = {2004},
month = {July},
abstract = {ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation. It includes measures to automatically determine the quality of a summary by comparing it to other (ideal) summaries created by humans. The measures count the number of overlapping units such as n-gram, word sequences, and word pairs between the computer-generated summary to be evaluated and the ideal summaries created by humans. This paper introduces four different ROUGE measures: ROUGE-N, ROUGE-L, ROUGE-W, and ROUGE-S included in the ROUGE summarization evaluation package and their evaluations. Three of them have been used in the Document Understanding Conference (DUC) 2004, a large-scale summarization evaluation sponsored by NIST.},
url = {http://approjects.co.za/?big=en-us/research/publication/rouge-a-package-for-automatic-evaluation-of-summaries/},
pages = {74-81},
}