Arabic document retrieval based on word rooting

Dissertant

al-Sarhan, Hind Hammud

Thesis advisor

al-Rababiah, Mamun

University

Al albayt University

Faculty

Prince Hussein Bin Abdullah Faculty for Information Technology

Department

Department of Computer Science

University Country

Jordan

Degree

Master

Degree Date

2013

English Abstract

In this research, an Arabic morphological system designed and implemented to extract Arabic roots.

Patterns play a big role in a process of extracting the root of the word, each word has its own pattern as in "يتفكرون ،يتفعلون " each letter in the word that replaces the letters ف،ع،ل in the pattern is considered as original letter and added to the root.

Efficient results are gotten that provide a good step in the process of minimizing the size of index structure.

The system was designed to accept input from a file or it can analyze one word at a time.

Words that the algorithm fails to analyze are normally foreign words, irregular words or words that do not have trilateral roots.

The new algorithms used in the proposed morphological analyzer are minimal in searching time.

The proposed system is directed to the modern Arabic.

It can resolve the inflected Arabic word, identify its root and finds its pattern.

Small components can be added to this system so that it will be capable of finding the verb tense and many other word attributes. This can be done using the information deduced by the proposed system and some extra linguistic rules.

Main Subjects

Information Technology and Computer Science

Topics

• Data processing
• Computational linguistics
• Arabic language

No. of Pages

66

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-414592