meaning extraction device, meaning extraction method, and program

摘要

A meaning extraction device (100) is provided with a clustering unit (102), an extraction rule generation unit (104), and an extraction rule application unit (108). The clustering unit (102) acquires feature vectors that transform numerical features representing the features of words having specific meanings and the surrounding words into elements, and clusters the acquired feature vectors into a plurality of clusters on the basis of the degree of similarity between feature vectors. The extraction rule generation unit (104) performs machine learning based on the feature vectors within a cluster for each cluster, and generates extraction rules to extract words having specific meanings. The extraction rule application unit (108) receives feature vectors generated from the words in documents which are subject to meaning extraction, specifies the optimum extraction rules for said feature vectors, and extracts the meanings of the words on the basis of which said feature vectors were generated by applying the specified extraction rules to said feature vectors.