出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：Extraction of semantic relations from various sources such as corpus, web pages, dictionarydefinitions etc. is one of the most important issue in study of Natural Language Processing(NLP). Various methods have been used to extract semantic relation from various sources.Pattern-based approach is one of the most popular method among them. In this study, wepropose a model to extract antonym pairs from Turkish corpus automatically. Using a set ofseeds, we automatically extract lexico-syntactic patterns (LSPs) for antonym relation fromcorpus. Reliability score is calculated for each pattern. The most reliable patterns are used togenerate new antonym pairs. Study conduct on only adjective-adjective and noun-noun pairs.Noun and adjective target words are used to measure success of method and candidateantonyms are generated using reliable patterns. For each antonym pair consisting of candidateantonym and target word, antonym score is calculated. Pairs that have a certain score areassigned to antonym pair. The proposed method shows good performance with 77.2% averageaccuracy.
关键词：Natural Language Processing; Semantic relations; Antonym; Pattern-based approach
