Font Size: a A A

Research And Implementation Of Intelligent Question Answering System In A Restricted Domain

Posted on:2009-04-06Degree:MasterType:Thesis
Country:ChinaCandidate:Y L WangFull Text:PDF
GTID:2178360245986891Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
In the age of Internet, with the online information explosive growth, people want to find information we need in the cyberworld fleetly and exactly. The information retrieval method based on the keyword or the simple logic-combination of the keywords has been unable to meet the people's need of information getting to a certain extent. Gradually Intelligent Question Answering System has grown to satisfy the people's need. In recent years, Chinese information processing technology's progress has greatly accelerated the Chinese Question Answering System's development. More and more foreign and domestic researchers of this direction began to given more energy toward the Chinese natural language Question Answering System. Question Answering System is the difficult and hot spots of current natural language processing domain. It combines natural language understanding and information retrieval techniques, etc. A Question Answering System can return user concise and accurate answers for question in natural language.At the present time , owing to the Chinese natural language complexity and processing technical limitations, let a computer to totally understand human language is very difficult. Therefore there is still no mature Question Answering System exploited by now. At the present stage Chinese Question Answering System is mainly based on specific domain.This paper revolves around design and implementation of Intelligent Question Answering System in a restricted domain, does a series of research aiming at the construction of domain knowledge, questions' comprehension and analysis, FAQ question matching, and so on. The FAQ question match is implemented by sentence similarity computation, and this model can answer frequently-asked question fast and concisely. Besides the system constructs theme document library taking advantage of web pages which Web crawler fetches. For the question which can not be answered by FAQ, the system will find answers from the theme document library. That is supplement and perfection of Question Answering System.
Keywords/Search Tags:IR, Question Answering System, FAQ, Language Model, Question Similarity
PDF Full Text Request
Related items