The aim of automatic indexing is to generate the descriptions that reflet document content so that descriptions may serve as document surrogates in text storage and retrieval systems. Popular approaches to automatic indexing are statistical analysis, syntactic processing techinque and semantic processing method.
This paper presents the design and implementation of an automatic indexing system in syntactic analysis approach. Among the several syntactic analysis methods available, this system adopts the Case Frame analysis which considers only the surface structure in a sentence. In this paper, it is assumed that extracting index terms from the surface case is sufficient, because what the case roles play in a sentences can account for the much of what the index terms are supposed to possess. The indexing procedure is realized in three parts; morpheme analysis; syntactic analysis; and the part which discards the useless words from the surface case and selects the proper nouns as index terms in the sentence.
