Unsupervised extractive summarization via coverage maximization with syntactic and semantic concepts

TY - GEN

T1 - Unsupervised extractive summarization via coverage maximization with syntactic and semantic concepts

AU - Schluter, Natalie Elaine

AU - Søgaard, Anders

PY - 2015

Y1 - 2015

N2 - Coverage maximization with bigram concepts is a state-of-the-art approach to unsupervised extractive summarization. It has been argued that such concepts are adequate and, in contrast to more linguistic concepts such as named entities or syntactic dependencies, more robust, since they do not rely on automatic processing. In this paper, we show that while this seems to be the case for a commonly used newswire dataset, use of syntactic and semantic concepts leads to significant improvements in performance in other domains.

AB - Coverage maximization with bigram concepts is a state-of-the-art approach to unsupervised extractive summarization. It has been argued that such concepts are adequate and, in contrast to more linguistic concepts such as named entities or syntactic dependencies, more robust, since they do not rely on automatic processing. In this paper, we show that while this seems to be the case for a commonly used newswire dataset, use of syntactic and semantic concepts leads to significant improvements in performance in other domains.

M3 - Article in proceedings

SN - 978-1-941643-73-0

VL - 2

SP - 840

EP - 844

BT - The 53rd Annual Meeting of the Association for Computational Linguistics (ACL)

PB - Association for Computational Linguistics

ER -