Digital learning for summarizing Arabic documents

Authors:
Mohamed Mahdi Boudabous;Mohamed Hédi Maaloul;Lamia Hadrich Belguith
Affiliations:
MIRACL Laboratory, Faculty of Economic Sciences and Management of Sfax, Sfax, Tunisia;LPL Laboratory, CNRS, Université de Provence, Aix en Provence, France;MIRACL Laboratory, Faculty of Economic Sciences and Management of Sfax, Sfax, Tunisia
Venue:
IceTAL'10 Proceedings of the 7th international conference on Advances in natural language processing
Year:
2010

Citing 4
Cited 0

A trainable document summarizer

SIGIR '95 Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval
Machine learning of generic and user-focused summarization

AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
The use of unlabeled data to improve supervised learning for text summarization

SIGIR '02 Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval
The automatic creation of literature abstracts

IBM Journal of Research and Development

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present in this paper an automatic summarization method of Arabic documents. This method is based on a numerical approach which uses a semi-supervised learning technique. The proposed method consists of two phases. The first one is the learning phase and the second is the use phase. The learning phase is based on the Support Vector Machine (SVM) algorithm. In order to evaluate our method, we conducted a comparative study that involves the results generated by our system AIS (Arabic Intelligent Summarizer) with that realized by a human expert. The obtained results are very encouraging and we plan to extend our evaluation on a larger corpus to ensure the performance of our system.