Enhancing quality Arabic web content through multilingual information retrieval methods

Dissertant

Safa, Abd al-Fattah

Thesis advisor

Yahya, Adnan

University

Birzeit University

Faculty

Faculty of Engineering and Technology

Department

Department of Computer Science

University Country

Palestine (West Bank)

Degree

Master

Degree Date

2019

English Abstract

Access to quality web content is an integral part of modern life.

While Arabic content is increasing rapidly, it is still far from adequate in terms of quantity, quality and timeliness and is well below what is available in many other languages.

To meet user needs, it helps to give Arabic users access to foreign web content.

The focus of the thesis is to grant Arabic users access to quality web content in other languages to meet their information needs.

This includes access to: textual data, structured databases and annotated multimedia elements.

For that we rely on Cross Lingual Information Retrieval (CLIR) concepts such as cross lingual document similarity, relevance measures, named entity recognition/transliteration, document quality assessment tools and knowledge extraction results [1,2].

Among the approaches we build on are Semantic Association (Explicit and Latent) [1,3,4], Knowledge Extraction [5,6,7] and Machine Translation and Transliteration [8].The methods developed will be utilized to increase the Arabic web content, to suggest material for further processing using crowd sourcing and, as a byproduct, for cross lingual plagiarism detection.

Main Subjects

Information Technology and Computer Science

No. of Pages

153

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-1413053