Research And Implementation On The Question Answering System In The Information Technology Domain

With the development and application of the Internet,the infomlation is growing rapidly.It hopes that we can obtain the information needed from the mass of the network content.The search engine has largely solved this problem.People only need to enter some keywords,and the search engine will return relevant pages. However,faced with so enormous infomation in pages,it is difficult for users to find what they need quickly.Therefore,in order to meet the desire that people are able to obtain infomation more quickly and accurately,automatic question answering(QA) system gradually developed.Automatic QA system allows users to use natural 1anguage to ask questions,and returns a concise and accurate answer to the problem.It uses a variety of natural 1anguag processing(NLP) techniques and it is one of the hot spots in computer application domain research.At present,the English QA system is more mature,but because of the complexity of the Chinese natural 1anguag,the Chinese question QA system is still at a preliminary stage.This paper researches a Chinese QA system in the IT domain.In this paper, according to the characteristics of IT domain knowledge, we design a Chinese QA system based on frequently—asked question(FAQ) in the Chinese Font Library.The system focuses on building IT domain knowledge library,computing sentence similarity algorithm and so on.In the part of building the IT domain knowledge base,we research and design the strcture of IT domain knowledge library,FAQ storage,FAQ pretreatment.In the part of sentence similarity computing,we use the similarity calculation algorithm based on semantic similarity.And we build the corresponding test set for the pilot test.In the last of the artical,we describe the experimental results and evaluation of the entire automatic QA system.The main contents of this paper are:(1) Analyzing the consisting framework of IT domain knowledge library.The framework in this thesis contains the QA knowledge library,domain thesaurus and erperts Q&A library.(2) Use the ICTCLAS technology segmentation word for question.Use sentences similarity calculation method based on semantic to calculation similarity between questions for the user and issues in the knowledge library,find matching questions and answers from the knowledge library,and then return knowledge to the user.(3) A FAQ answering system is designed and the Chiness Font Librart users can obtain the answers of frequent questions from this system.