De-suffixation for Downcorpusing
New Search | Print Abstract | E-mail Abstract | Full Text | Save to My Collections | Export Citation |
Abdukerim Janbaz, W., Saleh, I. & Duval, J. (2007). De-suffixation for Downcorpusing. In C. Montgomerie & J. Seale (Eds.), Proceedings of World Conference on Educational Multimedia, Hypermedia and Telecommunications 2007 (pp. 1028-1037). Chesapeake, VA: AACE.
Retrieved from http://www.editlib.org/p/25505.
Conference Information

World Conference on Educational Multimedia, Hypermedia and Telecommunications (EDMEDIA) 2007
Vancouver, Canada
June 25, 2007
ISBN 1-880094-62-2
Craig Montgomerie & Jane Seale
AACE
More Information on EDMEDIA
Table of Contents
Authors
Abstract
This paper is a mid-term report on the definition of suffixation rules for Modern Uyghur , an agglutinative Turkic language with complex vowel and consonant harmony features. Based on the correspondence between the lexical and surface levels, the paper reviews these features. It then concentrates on the morphology and order of succession of verbal suffixes. Rules are developed on that basis for computer information retrieval on Uyghur verbs as a basis for developing a complete system covering all lexical entities. The ultimate objective of this on-going research project is to propose a linguistic approach, rather than the traditional corpusing approach, for Uyghur NLP. This, in turn, can be applied to a spell check program as well as search, input and enhanced dictionary software using a lexical corpus simplified by the addition of suffixation rules for use in text processing and optical text recognition for Uyghur and for potential adaptation to closely related languages (Uzbek, Kazakh, Kyrgyz).
Keywords
Also Read
Tags
Add tagComments & Discussion
Comment on the paper above. You must be registered to participate. Registration is free.

New comment