Morphology-assisted Sindhi text analysis for natural language processing applications

Sodhar, Irum Naz and Sulaiman, Suriani and Buller, Abdul Hafeez (2023) Morphology-assisted Sindhi text analysis for natural language processing applications. Indian Journal of Science and Technology, 16 (35). pp. 2894-2901. ISSN 0974-6846 E-ISSN 0974-5645

Preview

PDF - Published Version Download (1MB) | Preview

Abstract

Understanding word construction and internal structure, especially in the Sindhi language, requires knowledge of the linguistic field known as morphology. In this study, Sindhi morphology is examined with particular attention paid to its structure, function, nature, word categories, and writing system. Natural Language Processing (NLP) relies on morphological analysis to identify words and their grammatical features, enabling applications like spell checkers and machine translation. A comparative analysis is done to comprehend how Sindhi Morphology developed. Because research on morphology analysis lack proper classification and cover both modern and conventional methodologies, Sindhi morphology variances present difficulties for computerization. Methods: Morphological analysis is crucial in Natural Language Processing (NLP) domains like spell checkers and gadget translation, studying word production and phrase shape using morphemes, the smallest grammatical elements in a language. Morphemes are the building blocks of words and are divided into free and fixed morphemes. Findings: Sindhi’s rich morphology and complexity enable borrowing and lending of words, but ambiguity is high due to similar patterns and vowel deletions. Morphological analysis influences semantic and syntactic analysis. Computerization is challenging due to prefixes, suffixes, and stem positions. Primary and secondary words can be subdivided into compound and complicated terms. The language uses initial, middle, and end writing styles. Novelty: This research aims to develop an automatic Sindhi morphological analyzer for future NLP applications, ensuring compatibility with existing Information Technology world applications. It will help understand Sindhi word structure and benefit software developers in developing Sindhi natural language and speech processing applications.

Item Type:	Article (Journal)
Uncontrolled Keywords:	Sindhi Morphology; Morphological Analysis; NLP; Communication and information sharing; Machine learning
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Information and Communication Technology Kulliyyah of Information and Communication Technology Kulliyyah of Information and Communication Technology > Department of Computer Science Kulliyyah of Information and Communication Technology > Department of Computer Science
Depositing User:	Dr. Suriani Sulaiman
Date Deposited:	29 Dec 2023 15:51
Last Modified:	30 May 2024 09:36
URI:	http://irep.iium.edu.my/id/eprint/109435

Actions (login required)

View Item