Automatic Recognition and Mining of Chinese Synonyms for Information Retrieval

摘要

Automatic recognition and mining of synonyms play an important role in information retrieval. In addition, it is broadly used in other applications, such as auto-indexing, auto-classification, auto-abstracting and machine translation ,etc. In order to enhance the mining ability of the synonyms, this paper presents two methods. The first method is pattern matching algorithm based on the mode of dictionary definition, we set some digging rules by hands, the system then digs synonyms by pattern matching automatically. The second method is the PageRank algorithm based on the definition in dictionary. We analyze the relation links between a given words and other words, then construct the associated word graph. Finally, we use the PageRank algorithm to calculate the similarity degree and discover synonyms in the associated word graph. The mining practice of financial dictionaries show that the precision of pattern matching algorithm and PageRank algorithm reach 90% and 85.6% respectively.