Research And Implementation Of Question Answering System For Biomedical Domain

With the explosion of information, the vast available information makes it an attractive resource for answering a variety of questions that users may have. Traditional search engines return a list of relevant documents but not the exact answers, and users often engage in perusing relevant information that they need manually. To overcome these shortcomings, more and more research organizations and companies do efforts to explore new generation of information retrieval systems. One of the most important directions is Question Answering (QA) system.Presently, many scientific research institutes have been investigated factoid questions frequently-asked questions (FAQ), some mature question-answering systems have been widely recognized. But few institutes are doing research on special domain and complex questions. According to the character of biomedical knowledge, this paper design and realize an automatic QA system in biomedical domain.This article is an exploration to biomedical question-answering system. This system is composed of three primary aspects: problem processing, information retrieving and answer extracting. In the different phases, different natural language process technologies will be used. In the phase of problem processing, the shallow parser is used to classify the questions availability, and the biomedical semantic resource is used to extend the key words of questions that can improve the recall. In the phase of answer extracting, in order to find context that include the information users want in documents, passage retrieval is used. Firstly, the corresponding paragraph is obtained. Second, the location of the passage is gotten by the hotsport. In order to save the time of users, we discard the repetitive or similar answers by computing sentence similarity when the system returns the answers to the users.The biomedical question-answering system has been experimented and evaluated on the data of TREC. The system can answer biomedical questions effectively from the results.