Volume 4, Issue 3, September 2018, Page: 79-83
Development of Longest-Match Based Stemmer for Texts of Wolaita Language
Girma Yohannis Bade, Department of Computer Science,Wolaita Sodo University, Wolaita, Ethiopia
Hussien Seid, Department of Computer Science and IT, Arba-Minch University, Arba-Minch, Ethiopia
Received: May 19, 2018;       Accepted: Jul. 5, 2018;       Published: Jul. 30, 2018
DOI: 10.11648/j.ijdst.20180403.11      View  389      Downloads  28
Abstract
This research presents design, experiment and development of longest-match based Stemmer for Wolaita texts. The objective of this paper is to conflate the variants of Wolaita text words into its stem with better accuracy, using Longest-Match based approach. To help the researcher how to compile the possible combination of suffixes, the deep analysis of Wolaita word morphology has been made. For data preprocess and implementation, C# programming language is used. After preprocessing, 12789 unique words are reserved to experiment this research. Out of these unique words, 1200 words are randomly selected earlier and kept separate for testing purpose. Then the developed stemmer was tested using Paice’s actual error counting method. The output on that test dataset has showed 91.84% accuracy over actual manually stemmed words. The obtained result shows that the rule based longest match approach is promising for stemming Wolaita language texts.
Keywords
Stemmer, Natural Language Processing, Morphology, Longest-Match
To cite this article
Girma Yohannis Bade, Hussien Seid, Development of Longest-Match Based Stemmer for Texts of Wolaita Language, International Journal on Data Science and Technology. Vol. 4, No. 3, 2018, pp. 79-83. doi: 10.11648/j.ijdst.20180403.11
Copyright
Copyright © 2018 Authors retain the copyright of this article.
This article is an open access article distributed under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Reference
[1]
Wardhaugh, R. Introduction to Linguistics. New York: McGraw-Hill Book Company, (1977).
[2]
Lemma Lessa. “Development of stemming algorithm for Wolaita text.” M. Sc. Thesis, Addis Ababa University, Department of Information Science, Addis Ababa,(2003).
[3]
Salton, G. & McGill, N. “Introduction to Modern Information Retrieval”. New York: McGraw-Hill, (1983).
[4]
Liddy, E. “Enhanced text retrieval using natural language processing.” Bulletin of the American Society for Information Science, 24, PP. 14-16, (1983).
[5]
Schinke, R, et al. "A Stemming Algorithm for Latin Text Databases." In Journal of Documentation. 52(2), PP. 172 – 187, (1996).
[6]
Lamberti, Marcello and Sottile, Roberto. ”The Wolaita Language. Koln: Rudiger Koppe Verlag.”, (1997).
[7]
Paice C. D. “An Evaluation Method for Stemming Algorithms”. ACM SIGIR Conference on Research and Development in Information Retrieval. 1994, 42-50.
[8]
McGregor, W., (2009). Linguistics: An Introduction. London: Continuum International Publishing Group.
[9]
Debela T, Ermias. Designing a Rule Based Stemmer for Afaan Oromo Text. International Journal of Computational Linguistics (IJCL), Volume (1): Issue (2), October 2010.
[10]
Dawson J. L., 1974: "Suffix removal and word connation," ALLC Bulletin, 2(3), 33-46.
Browse journals by subject