Research And Implementation Of Chinese Question Answering System For Respirology

Question answering system is an important research topic in the field of natural language processing.Compared with the traditional search engines,question answering system can meet the needs of the users more perfectly.At present,lots of researches have been conduced abroad,which leads to relatively complete systems,while the domestic researches are relatively little.We present a semantic analyzing algorithm combining shallow parsing and the maximum entropy on the basis of constructing respiratory domain ontology.Firstly,questions are identified by semantic blocks.If the recognition is succeeds,the question vectors are formed and then the SPARQL query is performed on the ontology.Otherwise,the maximum entropy model is invoked to judge the semantic role of the question.We use the maximum entropy model to train annotated corpus,which extracts the semantic block features to determine the most probable sentence pattern and form question vector,and then query through ontology to get the answers.Based on the semantic analyzing algorithm,we finally implement a Chinese question answering system for respirology,which can analyze nature language questions and return related answers.Compared with other methods,the novel algorithm has higher precision and recall rate.