Title: Toward an automatic summarisation of Arabic text depending on rhetorical relations

Authors: Samira Lagrini; Nabiha Azizi; Mohammed Redjimi; Monther Al Dwairi

Addresses: Labged Laboratory, Computer Science Department, Badji Mokhtar University, P.O. Box 12, Annaba, 23000, Algeria ' Labged Laboratory, Computer Science Department, Badji Mokhtar University, P.O. Box 12, Annaba, 23000, Algeria ' Universite 20 Aout 1955 – Skikda, 21000, Algeria ' College of Technological Innovation, Zayed University, P.O. Box 144534, Abu Dhabi, UAE

Abstract: Rhetorical relations between two text segments are crucial information and have been proven useful for many natural language processing applications. In this paper, we propose a supervised approach for automatic identifying of rhetorical relations in Arabic texts. Our model attempts to identify both implicit and explicit rhetorical relations between elementary discourse units which will be exploited in automatic summarisation of Arabic texts. To carry out this research, we developed a discourse annotated corpus following the rhetorical structure theory framework with high reliability. Relations annotation was done using a set of 23 fine-grained relations enriched with nuclearity annotation. To automatically learn these relations, we reuse some state of the arts features and contribute new lexical and semantics' features. The experimental results on fine-grained and coarse-grained relations show that our model achieved best performance relative to all baselines.

Keywords: rhetorical relations; Arabic language; rhetorical structure theory; text summarisation.

DOI: 10.1504/IJRIS.2019.102533

International Journal of Reasoning-based Intelligent Systems, 2019 Vol.11 No.3, pp.203 - 214

Received: 27 Dec 2017
Accepted: 16 Jun 2018
Published online: 30 Sep 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article