Automatic Arabic Text Summarization System (AATSS) Based on Semantic Features Extraction

Automatic Arabic Text Summarization System (AATSS) Based on Semantic Features Extraction

Nabil M. Hewahi (Bahrain University, Bahrain) and Kathrein Abu Kwaik (Al Azhar University, Palestine)
Copyright: © 2012 |Pages: 16
DOI: 10.4018/jtd.2012040102


Recently, the need has increased for an effective and powerful tool to automatically summarize text. For English and European languages an intensive works have been done with high performance and nowadays they look forward to multi-document and multi-language summarization. However, Arabic language still suffers from the little attentions and research done in this filed. In this paper, we propose a model to automatically summarize Arabic text using text extraction. Various steps are involved in the approach: preprocessing text, extract set of features, classify sentence based on scoring method, ranking sentences and finally generate an extracted summary. The main difference between the proposed system and other Arabic summarization systems are the consideration of semantics, entity objects such as names and places, and similarity factors in our proposed system. The proposed system has been applied on news domain using a dataset osbtained from Local newspaper. Manual evaluation techniques are used to evaluate and test the system. The results obtained by the proposed method achieve 86.5% similarity between the system and human summarization. A comparative study between our proposed system and Sakhr Arabic online summarization system has been conducted. The results show that our proposed system outperforms Shakr system.
Article Preview

1. Introduction

As the amount of information rapidly grows on the internet, there are a lot of difficulties to select the relevant information we need to satisfy our requirements. Furthermore, publications media varies from specialist journals to newspapers to many other versions.

Summarization of texts or Text Summarization (TS) appears as the best solution for users to choose and decide if this document will help her/him or not. Summarization is the process of producing shorter and informative presentation of the most important information from a source or multiple sources of information according to particular needs and specifications. Summarization is not applied only on text documents but also on any multimedia facility. Summarization of text documents became a very important issue due to the very large text sources already available. Users tend to extract the most informative and/or indicative information instead of reading the whole original document(s) (Sobh, 2006).

Radev and Mckeown (2002) define a summary as “a text that is produced from one or more texts, which convey important information in the original text, and that, is no longer than half of the original text(s) and usually significantly less than that”.

Currently, the areas of automatic text summarization are extensive. TS can be useful in many fields such as medical area, legal area and news area. There are several, often related views which can be used to characterize text summarization. The main categories used to classify summarization are: 1) Number of documents (single or Multi), 2) Number of Language (Mono-language or Multi-languages), 3) Forms of Summary which are classified into two types abstractive summarization and extractive summarization. Abstractive summarization is the hardest task for computer researchers to solve as it is concerned with semantic and language complexity. The summary containing sequence of words not present in the original document. Extractive summarization consists of words, sentences and paragraphs that are completely appear in the original document. This approach suffers from inconsistencies, lack of balance and lack of cohesion. Also some sentence may be extracted out of the context and anaphoric references can be broken (Ježek & Steinberger, 2007).

Research in Arabic Natural Language Processing (ANLP) has focused on the manipulation and processing of the structure of the language at morphological, lexical, and syntactic levels. Unfortunately, semantic processing of the Arabic language has not yet received enough attention (Haddad & Yassen, 2005).

There are some aspects that slow down progress in Arabic Natural Language Processing compared to the accomplishments in English and other European languages including (Diab, Jurafsky, & Hacioglu, 2007):

  • 1.

    The complex morphology;

  • 2.

    the absence of diacritics in written text;

  • 3.

    The fact that Arabic does not use capitalization.

In addition to the above linguistic issues, there is also a shortage of Arabic corpora, lexicons and machine readable dictionaries. These tools are essential to advance research in different areas. Despite these difficulties, there has been some success in tackling the problem of Arabic syntax as in Al-Shammari and Lin (2008); Elabbas (2005). Few attempts have been made to develop Automatic Arabic summarization systems as in Abdallah, Aloulou, and Belguith (2008); Douzidia and Lapalme (2004).

In our paper we present an automatic Arabic summarization system based on extraction summarization for a single document with consideration for semantics, synonumous and for entity objects objects such as names, locations and special terminologies.

The next section will be focused on the related work. Section three is devoted to the proposed system. Section four discusses the experimental results and system evaluation. Section five presents the conclusion and the future directions.

Complete Article List

Search this Journal:
Open Access Articles
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing