The BITQAP question answering platform is ontology-based semantic question answering system. In "Computer Organization and Architecture" course, we apply the platform as CAI tools to answer questions. In the paper, we proposed methods to extract the concepts and relations from course corpus. Term extraction is the first step of ontology learning. The Chinese domain terms have three features: Coupling, Domain Relevancy and Domain Consensus. In the paper, these features be modeled and integrated to evaluate the terms. In concept learning process, the CBC (Clustering by Committee) is adopted to learn concepts. In relation learning process, snow ball technique to be used to acquire hyponymy relation, and HowNet-based method to be used to extract general relation. Experimental results show that the methods of ontology learning in the paper is efficient and is helpful to solving of semantic problems in question answering system.
Question classification is very important in question answering system. This paper presents our research about question classification in a real-world on-line interactive question answering system in computer service & support domain. In the domain, questions are divided into 15 cursory categories and 220 sub-categories. The difference of this system is that standard question sentences represent the subcategories rather than only classification criterion. For the special situation, the two level question classification method is present in the paper. Support Vector Machine method is adopted to train a classifier on coarse categories; question semantic similarity model is used to classify the question into sub-categories. The lexical feature and domain ontology concept hierarchy is constructed and exploited to enhance the expression capacity of the feature characteristic for both feature selection for SVM and question semantic similarity computing. When trained and tested on the 11000 question instances in the domain, our approach reaches an accuracy up to 91.5%, which outperforms the result of the baseline.
IQA system has been attracted by researchers in recent years. Through interactive dialogue with the user, IQA systems can gradually clear the real intention of the user's questions. In this paper, we introduced an architecture of IQA system which is based on an IQA ontology and adopting hybrid reasoning mechanism. Our supposed IQA system can online diagnose the fault and return the corresponding solutions by interactive dialogue with the user. The method is mainly concerned about two aspects of IQA system: interactivity and the ontology knowledge base which is suitable to achieve such interactivity. The results of experiment show that the system is feasible and usable.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.