The Research on Automatic Acquirement of the Domain Terms

There are different features in domain terms on different domain. In this paper, we took TCM clinical symptom terms as example to discuss the acquirement of domain terms due to the particularity and complexity in clinical symptom terms. We analyze the feature of TCM clinical symptom terms, and define the formal representation of the word-formation. Then we use the term in the TCM Clinical Terminology as seed terms, and generate word-formation rule base. We recognize the new TCM clinical symptom terms in the medical records based on the word-formation rule base. Then we verify the recognized terms with statistical method to implement the automatic recognition of TCM clinical symptom terms, as the basis of data analysis and data application in the further.