NATURAL LANGUAGE PROCESSING APPARATUS AND PROGRAM

To provide a natural language processing apparatus and program for obtaining a distributed vector of a classification word comprehensively representing a purpose of a sentence associated with the classification word.SOLUTION: A natural language processing apparatus includes: a first calculation section (distributed representation model generation processing S20) that calculates a distributed vector of a word included in a plurality of sentences on the basis of a database that manages the plurality of sentences associated with a classification word; a second calculation section (enterprise vector calculation processing S22) that calculates a distributed vector of the sentence on the basis of the distributed vector of the word included in each sentence; and a third calculation section (business characteristic word vector calculation processing S24, business type vector calculation processing S26) that calculates a distributed vector of the classification word on the basis of the distributed vector of each sentence associated with the same classification word.SELECTED DRAWING: Figure 20 【課題】分類語に紐づけられるセンテンスの趣旨を総括的に示す分類語の分散ベクトルを求める自然言語処理装置及びプログラムを提供する。【解決手段】自然言語処理装置は、分類語に紐づけられる複数のセンテンスを管理するデータベースに関して、複数のセンテンスに含まれる単語の分散ベクトルを算出する（分散表現モデル生成処理Ｓ２０）第１算出部と、各センテンスに含まれる単語の分散ベクトルに基づいて、当該センテンスの分散ベクトルを算出する（企業ベクトル算出処理Ｓ２２）第２算出部と、同じ分類語に紐づけられる各センテンスの分散ベクトルに基づいて、当該分類語の分散ベクトルを算出する（事業特性ワードベクトル算出処理Ｓ２４、業種ベクトル算出処理Ｓ２６）第３算出部と、を備える。【選択図】図２０