A new knowledge acquisition method from TCM clinical cases based on information extraction

In traditional Chinese medicine (TCM), clinical cases are viewed as semi-structured text, which is between free text and structured text. Their characteristic is lack for grammar, having no strict format, and even uncompleted sentences. But, clinical cases is an important knowledge source, the knowledge acquisition from which are going urgently for inheriting TCM. In this paper, a new machine learning method was proposed for the information extraction TCM clinical cases based on structured templates. This method is an interactive processes with a domain expert. If we use uniform templates to describe the TCM clinical cases, they will not only result the loss of some information, but also not reflect the every expertpsilas experience knowledge perfectly. In this paper, EPTCMR, a method of extraction template from TCM clinical cases is proposed, which is based on domain ontology of TCM.