Work

Enhancing Root Extractors Using Light Stemmers

Year: 2015

Type: conference-paper

Abstract: The rise of Natural Language Processing (NLP) opened new possibilities for various applications that were not applicable before. A morphological-rich language such as Ara-bic introduces a set of features, such as roots, that would assist the progress of NLP. Many tools were developed to capture the process of root extraction (stemming). Stemmers have improved many NLP tasks without explicit knowledge about its stemming accuracy. In this paper, a study is conducted to evaluate various Arabic stemmers. The study is done as a series of comparisons using a manually annotated dataset, which shows the efficiency of Arabic stemmers, and points out potential improvements to existing stemmers. The pa-per also presents enhanced root extractors by using light stemmers as a preprocessing phase. 1

Source: Institutional Repositories DataBase (IRDB)

Authors: Mahmoud El-Defrawy, Yasser El-Sonbaty, Nahla A. Belal

Institution: Arab Academy for Science, Technology, and Maritime Transport

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2394855683

FWCI: 0.939

Cites: 22

Cited by: 11

Related to: 10