Word stemming challenges in Malay texts: a literature review

• Main Authors: Kassim, M. N., Maarof, M. A., Zainal, A., Wahab, A. A.
• Format: Conference or Workshop Item
• Published: Institute of Electrical and Electronics Engineers Inc. 2016
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.utm.my/id/eprint/73081/; https://www.scopus.com/inward/record.uri?eid=2-s2.0-84992159871&doi=10.1109%2fICoICT.2016.7571887&partnerID=40&md5=01b187fded8720a6095b412147e367ae

Word stemming algorithm is used in artificial intelligence applications to stem derived words to their respective root words. Even though there are many existing words stemming algorithms for the Malay language have been proposed in the past years, there is still a need for an effective word stemming algorithm to address word stemming challenges due to the complexity of Malay language. Thus, this paper will highlight three main word stemming challenges in the existing word stemming algorithms namely morphological rules of Malay language, word patterns in digital Malay texts and word stemming evaluation. Hence, these stemming challenges will be considered in future development of an effective word stemming algorithms for the Malay language.