How far we can go with extractive text summarization? Heuristic methods to obtain near upper bounds

作者:

Highlights:

• We propose 9 heuristics to construct near upper bounds for extractive summarization.

• The proposed methods are faster and have close results to the exhaustive search.

• We construct the sentence-based and word-based near upper bounds for 5 different corpora.

• We evaluate 6 general extractive summarization methods across the 5 corpora.

摘要

•We propose 9 heuristics to construct near upper bounds for extractive summarization.•The proposed methods are faster and have close results to the exhaustive search.•We construct the sentence-based and word-based near upper bounds for 5 different corpora.•We evaluate 6 general extractive summarization methods across the 5 corpora.

论文关键词:Extractive text summarization,Upper bound construction,Ideal extracts construction,Summarization evaluation

论文评审过程:Received 18 May 2017, Revised 21 August 2017, Accepted 22 August 2017, Available online 25 August 2017, Version of Record 31 August 2017.

论文官网地址:https://doi.org/10.1016/j.eswa.2017.08.040