Events Automatic Extraction from Arabic Texts

Events Automatic Extraction from Arabic Texts

Emna Hkiri (University of Monastir, Tunisia), Souheyl Mallat (University of Monastir, Tunisia) and Mounir Zrigui (University of Monastir, Tunisia)
DOI: 10.4018/978-1-7998-0951-7.ch078


The event extraction task consists in determining and classifying events within an open-domain text. It is very new for the Arabic language, whereas it attained its maturity for some languages such as English and French. Events extraction was also proved to help Natural Language Processing tasks such as Information Retrieval and Question Answering, text mining, machine translation etc… to obtain a higher performance. In this article, we present an ongoing effort to build a system for event extraction from Arabic texts using Gate platform and other tools.
Chapter Preview

2. Arabic Language

In Arabic processing domain, the research started in the 1970, even before editing texts problems are fully solved. Early studies focused mainly on lexicons. For ten years, the Web internationalization and the proliferation of media in Arabic demonstrated the usefulness of a large number of potential applications of the Arabic NLP. Therefore, researches have begun to address issues more varied as syntax, automatic translation, automatic indexing of documents, information retrieval, etc. (Farber; 2008).

In what follows, we present orthographic and morphological systems of the Arabic language and some problems of its automatic processing as the lack of free resources, lack of vowels and the agglutination of words. Those are the main issues that characterize Arabic and strongly contribute to the delay of its automatic processing. For morphological analysis, the absence of vowels adds additional ambiguity of Arabic words. As for the agglutination, it makes it more difficult to identify the segments that make up these words.

Complete Chapter List

Search this Book: