Information extraction device, information extraction method and information extraction program

摘要

To provide an information extraction device, an information extraction method, and an information extraction program capable of accurately extracting documents having similar contents.SOLUTION: An information extraction device 1 includes: an input unit 11 configured to receive an input of a key document serving as a search key; a first feature quantity calculation unit 12 configured to calculate a feature quantity based on a word included in the document; a first similarity calculation unit 13 configured to calculate, for the feature quantity of the key document, a first similarity with respect to the feature quantity of each of a plurality of search target documents accumulated in the past; an output unit 14 configured to output a search result based on the first similarity; and an evaluation unit 15 configured to receive an evaluation value for the search result and store the evaluation value in association with a combination of a word group included in the key document and a word group included in the search result. The first feature quantity calculation unit 12 calculates, based on the evaluation value, a bias value related to a distance between a word included in the key document and another word and incorporates the calculated bias value in the feature quantity. The first similarity calculation unit 13 adjusts the first similarity on the basis of the bias value.SELECTED DRAWING: Figure 2