Patent Term Extraction by Integrating Keyword Knowledge From Paper

Abstract: [Purpose/significance] In order to make up for the shortcomings of the patent text collection itself to limit the effect of patent term extraction, this paper proposes to use the rich keyword knowledge to obtain effective features outside the patent text to improve the patent term extraction effect. [Method/process] According to the keyword knowledge of related papers, two kinds of characteristic, degree of domain relevance and degree of head & tail are proposed to measure the possibility that candidate terms become terminology, and these characteristics are incorporated into the traditional method of patent term extraction. [Result/conclusion] The experimental results show that the degree of domain relevance and the degree of head & tail of the candidate terms obtained by using the keyword information of the papers make the method of combining the keyword knowledge of the papers significantly higher than the accuracy of the traditional term extraction method.