Apparatus and Method for searching information based on Wikipedia's contents

摘要

The present invention relates to an information retrieval apparatus and an information retrieval method based on Wikipedia contents, and an embodiment according to the present invention is an information retrieval apparatus and an information retrieval method based on contents of a Wikipedia, in which a body document, a section title document, an infobox document, Extracting an index word of the part-of-speech unit from the query response wikipedia document, and generating an index of a wikipedia document for a query response by analyzing the wikipedia document for the query response, A query analyzing unit that receives a natural language query, analyzes a question type, a correct answer type, and a question focus in the natural language query, and extracts a document retrieval keyword; a retrieval unit that retrieves the document retrieval keyword from the Wikipedia To perform a document search, and for each of the above query responses An answer extracting unit for extracting a first correct answer using the question type, the correct answer type, and the question focus from the document search result, a document retrieval unit for generating a document retrieval result from the keypadia document index, And a correct answer integrating unit for integrating and ranking the correct answers and generating a second correct answer based on the contents of the Wikipedia.