Extraction of Explanation Based Symptom-Treatment Relation from Texts

This paper aims to extract the explanation-based Problem-Solving relation, especially the Symptom-Treatment relation, from hospital-web-board documents. The extracted relations benefit people who are learning how to solve their health problems. The research includes three main problems: 1) how to identify symptom-concept EDUs (where an EDU is an elementary discourse unit or a simple sentence/clause) and treatment concept EDUs, 2) how to identify the symptomconcept-EDU boundary and the treatment-concept-EDU boundary as an explanation, 3) how to determine SymptomTreatment relations from documents. Therefore, we propose collecting each Multi-Word-Co occurrence with either a symptom concept or a treatment concept from a verb-phrase to identify each symptom-concept EDU and each treatment-concept EDU including their boundaries. Collecting Multi-Word-Co involves two more problems of the ambiguous Multi-Word-Co and the Multi-Word-Co size. Thus, we apply the Bayesian Network to solve both problems of Multi-Word-Co after applying word rules. The Symptom-Treatment relation can be solved by Naive Bayes learning vector pairs of symptom vectors and treatment vectors. The research results can provide high precision when extracting Symptom-Treatment relations through texts.