Abstract:
URI 정의문및 부가정보기반텍스트에서개체의 URI를식별하는장치, 토픽분포추정방법및 URI 선택방법이개시된다. 여기서, 장치는모든 URI(Uniform Resource Identifier)에대한정의문및 부가정보로구성된 URI 문서집합에대하여추정된토픽분포로부터개별 URI 문서의토픽분포를생성하는토픽분포추정부, 그리고 URI 식별대상인개체표면형을포함한질의텍스트가입력되면, 상기질의텍스트로부터상기개체표면형을추출하고, 상기질의텍스트의토픽분포를추정하며, 상기토픽분포를기초로상기개체표면형에해당하는 URI를선택하는 URI 선택부를포함한다.
Abstract:
The present invention relates to an owl based ontology which is useful for tagging a part of speech of a word forming a Korean text and, more specifically, to an owl based ontology expression method for using a Korean sentence for tagging a part of speech used in a system for processing a natural language.
Abstract:
The present invention relates to a schedule management service system in a wired/wireless communications network, and more specifically, to a schedule management service system for automatically extracting information on a schedule of a user from the Internet, processing the extracted information into a time table form, and automatically providing the processed information to the user according to a time-flow.
Abstract:
PURPOSE: A natural language text representation method is provided to enable a computer to understand a text by changing a text into a mechanical expression. CONSTITUTION: A sentence separates from a subject part and a predicate part. The subject part and the predicate part are connected by using a relation word. A verb is separated from a component verb. The predicate part and the verb are connected by using a related term. The subject part and head noun are connected by using the related term.