Arabic light stemmer based on regular expression technique

المؤلفون المشاركون

al-Badarinah, Mutasim
Mahyub, Nizar
Shihab, Muhammad A.
al-Shalabi, Riyad
Kanan, Ghassan

المصدر

International Computer Sciences and Informatics Conference, Amman, Jordan 12-13 January 2016.

الناشر

جامعة عمان العربية

تاريخ النشر

2016-01-31

دولة النشر

الأردن

عدد الصفحات

9

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

الملخص الإنجليزي

Arabic light stemmer removes affixes from any word as well as stop words.

It is considered as a text pre-processing task for many Natural Language Processing (NLP) applications such as text categorization, information retrieval, opinion mining, etc..

Many Arabic light stemmers were presented are depend on several techniques like the grammar-based, patterns-based, and mathematical rules-based.

In this paper, a new Arabic stemmer based on regular expressions is proposed, where it relies on regular expression to check out if the inputted word related to its text pattern or not.

This stemmer is designed with two modes : (i) using only the proposed regular expression methodology, while (ii) hiring the Microsoft Word dictionary in addition to the proposed stemmer.

The proposed methods achieved remarkable results that vary between 73.3% and 79.6% accuracy.

نوع البيانات

أوراق مؤتمرات

رقم السجل

BIM-767331

• APA
• MLA
• AMA