How to resolve ambiguity in the language of natural language information retrieval

摘要

The present invention relates to a method for resolving ambiguity in words of natural language information retrieval.;Recently, an information retrieval system that processes a myriad of document information, extracts only information corresponding to a user's request, and provides the information to a user is widely used. However, in general, it is very difficult to extract the information required by the information requester from a large set of documents. Also, in the Korean information retrieval system, due to the ambiguity of the word itself due to the homonym, the wrong result in the natural language indexing or retrieval There is a problem that causes.;In order to solve this problem, the present invention uses a mutual information network that automatically establishes a relationship between a keyword of a query and keywords in a first searched document for documents searched first before presenting a finally ordered document to a user. Once again, a method of resolving the ambiguity of natural language information retrieval that can improve the efficiency of information retrieval by presenting the search results by reordering according to the more meaningful degree of relevance is proposed.