期刊名称：Oriental Journal of Computer Science and Technology
印刷版ISSN：0974-6471
出版年度：2010
卷号：3
期号：1
页码：89-93
出版社：Oriental Scientific Publishing Company
摘要：Natural language processing has wide coverage in application areas like machine translation, text to speech conversion , semantic analysis , semantic role labeling and knowledge representation.Morphological and syntactic processing are components of NLP which process each word to producethe syntactic structure of the sentence, with respect to its grammar .Semantic analysis follows syntacticanalysis. One of the key task in morphological analysis is identifying the correct root word from itsinflected form.In Sanskrit language, these inflected word follow the rules which are used to separatethe root word from its suffix.These extracted suffix carry sufficient amount of syntactic and semanticinformation with them .To develop such word splitter, rules called sandhi rules given in the grammar ofthe Sanskrit language has been used.The challenge in the problem lies is in identifying the junctionpoint or breaking point of the word as multiple junction can be obtained within the word .Developedsystem maintains database of all possible suffix , which are then used for splitting the word . Thealgorithm for the same is presented in the paper with the solutions to problem faced while developingthe module
关键词：Vibhakti ;Semantic analysis; vibhakti-karka mapping and splitter
