The temporal relation or temporal links (denoted by the TLink tag) in Chinese electronic medical records includes temporal relations within a sentence (hereafter referred to as "within-sentence TLinks"), and between-sentence TLinks. Among them, within-sentence TLinks include event/event TLinks and event/time TLinks, and between-sentence TLinks include event/event TLinks. The recognition of temporal relation in Chinese electronic medical record was transformed into classification problem on entity pairs. Heuristic rules with high accuracy were developed and two different classifiers with basic features, phrase syntax, dependency features, and other features were trained to determine within-sentence TLinks. Apart from heuristic rules with high accuracy, basic features, phrase syntax, and other features were used to train the classifiers to determine between-sentence TLinks. The experimental results show that Support Vector Machine (SVM), SVM and Random Forest (RF) algorithms achieve the best performance of recognition on within-sentence event/event TLinks, within-sentence event/time TLinks and between-sentence event/event TLinks, with F ₁-scores of 84.0%, 85.6% and 63.5% respectively.

Since the hyponymy between symptoms has strong structural features, an automatic hyponymy extracting method based on symptom components was proposed. Firstly, it was found that symptoms can be divided into eight parts: atomic symptoms, adjunct words, and so on, and the composition of these parts satisfied certain constructed rules. Then, the lexical analysis system and Conditional Random Field (CRF) model were used to segment symptoms and label the parts of speech. Finally, the hyponymy extraction was considered as a classification problem. Symptom constitution features, dictionary features and general features were selected as the features of different classification algorithms to train the models. The relationship between symptoms were divided into hyponymy and non-hyponymy. The experimental results show that when these features are selected simultaneously, precision, recall and F1-measure of Support Vector Machine (SVM) are up to 82.68%, 82.13% and 82.40%, respectively. On this basis, by using the above hyponymy extracting algorithm, 20619 hyponymies were extracted, and the knowledge base of symptom hyponymy was built.