Efficient and Effective Single-Document Summarizations and a Word-Embedding Measurement of Quality

Liqun Shao, Hao Zhang, Ming Jia, Jie Wang

2017

Abstract

Our task is to generate an effective summary for a given document with specific realtime requirements. We use the softplus function to enhance keyword rankings to favor important sentences, based on which we present a number of summarization algorithms using various keyword extraction and topic clustering methods. We show that our algorithms meet the realtime requirements and yield the best ROUGE recall scores on DUC-02 over all previously-known algorithms. To evaluate the quality of summaries without human-generated benchmarks, we define a measure called WESM based on word-embedding using Word Mover’s Distance. We show that the orderings of the ROUGE and WESM scores of our algorithms are highly comparable, suggesting that WESM may serve as a viable alternative for measuring the quality of a summary.

Download


Paper Citation


in Harvard Style

Shao L., Zhang H., Jia M. and Wang J. (2017). Efficient and Effective Single-Document Summarizations and a Word-Embedding Measurement of Quality.In Proceedings of the 9th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, ISBN 978-989-758-271-4, pages 114-122. DOI: 10.5220/0006581301140122


in Bibtex Style

@conference{kdir17,
author={Liqun Shao and Hao Zhang and Ming Jia and Jie Wang},
title={Efficient and Effective Single-Document Summarizations and a Word-Embedding Measurement of Quality},
booktitle={Proceedings of the 9th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR,},
year={2017},
pages={114-122},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006581301140122},
isbn={978-989-758-271-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR,
TI - Efficient and Effective Single-Document Summarizations and a Word-Embedding Measurement of Quality
SN - 978-989-758-271-4
AU - Shao L.
AU - Zhang H.
AU - Jia M.
AU - Wang J.
PY - 2017
SP - 114
EP - 122
DO - 10.5220/0006581301140122