APPARATUS FOR CREATING ALIGNMENT CORPUS BASED ON UNSUPERVISED ALIGNMENT AND METHOD THEREOF, AND APPARATUS FOR PERFORMING MORPHOLOGICAL ANALYSIS OF NON-CANONICAL TEXT USING THE ALIGNMENT CORPUS AND METHOD THEREOF

摘要

Disclosed are an alignment corpus generation device based on unsupervised learning alignment, a method thereof, a morphological analysis device for analyzing non-canonical expressions using alignment corpus, and a morphological analysis method thereof. The morphological analysis device includes a knowledge database and an analyzer. The knowledge database stores a plurality of knowledge items used for morphological analysis in each language and includes: a morpheme dictionary in which morpheme data corresponding to canonical expressions and an aligned corpus in which canonical expressions corresponding to non-canonical expressions - wrong-spelled expressions and unnormalized or unstandardized expressions- are stored. The analyzer performs morphological analysis of an inputted phrase using the knowledge database and outputs the analysis result. If no morpheme exists for the inputted phrase in the morpheme dictionary, the present invention preforms morphological analysis by finding a canonical expression corresponding to the non-canonical expression using the alignment corpus for the non-canonical expression included in the inputted phrase.