A Study on a Bank-Domain Automatic Chinese Question-Answering System BAQS

The background and system frame of the system BAQS are presented. A new approach is explored in which questions are analyzed based on the detection of question focus chunk, semantic chunk and question template. Then vectors are used for the whole semantic representation. With the elicitation of ontology and Hownet, a bank ontology database and bank Hownet are built up. The finance domain texts are annotated in the head, and then the answer extracted from the tag trees by the question vector. For a specific bank a question-answering system is implemented and experiments do prove that it is feasible to use the method to develop a domain question-answering system, that is valuable for further study in more depth.