A Construction Method for the Semantic Relation Corpus of Traditional Chinese Medicine

It is difficult to use a search engine to acquire knowledge directly due to the complexity of Web resources. In this paper we proposed a method for semantic relation corpus construction of traditional Chinese medicine based on combination of multiple encyclopedias. For a known conceptual pair, we got some search results by automatically constructing search requests based on URLs’ characteristics of the encyclopedia search engine, and used regular expressions to extract meaningful texts from the search results to form semantic relation corpus. The experiment result shows that the precision and recall are 92.1% and 65.3%, respectively.