意味ネットワークの経時変化で表現された計算論的なコンセプト創出モデルとその実装

DOI Web Site オープンアクセス

書誌事項

タイトル別名
  • A Computational Concept Invention Model Represented by Time-varying Semantic Network and Its Implementation
  • イミ ネットワーク ノ ケイ ジヘンカ デ ヒョウゲン サレタ ケイサンロンテキ ナ コンセプト ソウシュツ モデル ト ソノ ジッソウ

この論文をさがす

抄録

 Automatic creation of concepts is important for various situations. Previous re-<br>searches in the conceptual blending and the concept invention proposed the cognitive<br> models which represent the process by which people combine concepts and those rela-<br>tionships. However, those researches do not allow one to create new concepts automat-<br>ically in the real world, where there are innumerable notions and the meanings of them<br> are time-varying. Because the previous models can not discover which notions should<br> be combined to create successful concepts, it is necessary for a user to find an appro-<br>priate combination of notions. There are approximately 50 million combinations in the<br> business domain. Therefore, we propose a novel model representing concept creation<br> processes, which makes automatic creation of new and successful concepts possible even<br> in such a real world setting. We formalize the concept creation process as discovering<br> new connections between existing concepts and it can be mathematically represented<br> using the chronological change of the semantic networks. The data of the input and<br> output of this process can be built using a large document set. Hence, machine learning<br> technique can reveal a law underlying the concept creation process. After extracting<br> such a law, the machine learning model can provide new concepts in accordance with<br> its law. In experiments, we evaluated the validity of this approach using real successful<br> concepts and document sets, and created new concepts in food category.

収録刊行物

  • 認知科学

    認知科学 24 (1), 33-51, 2017

    日本認知科学会

関連プロジェクト

もっと見る

詳細情報

問題の指摘

ページトップへ