An Evolutionary Algorithm for Automatic Summarization

Aurélien Bossard, Christophe Rodrigues


Abstract
This paper proposes a novel method to select sentences for automatic summarization based on an evolutionary algorithm. The algorithm explores candidate summaries space following an objective function computed over ngrams probability distributions of the candidate summary and the source documents. This method does not consider a summary as a stack of independent sentences but as a whole text, and makes use of advances in unsupervised summarization evaluation. We compare this sentence extraction method to one of the best existing methods which is based on integer linear programming, and show its efficiency on three different acknowledged corpora.
Anthology ID:
R17-1017
Volume:
Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
Month:
September
Year:
2017
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
111–120
Language:
URL:
https://doi.org/10.26615/978-954-452-049-6_017
DOI:
10.26615/978-954-452-049-6_017
Bibkey:
Cite (ACL):
Aurélien Bossard and Christophe Rodrigues. 2017. An Evolutionary Algorithm for Automatic Summarization. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 111–120, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
An Evolutionary Algorithm for Automatic Summarization (Bossard & Rodrigues, RANLP 2017)
Copy Citation:
PDF:
https://doi.org/10.26615/978-954-452-049-6_017