When we humans receive uncertain information, we interpret it suitably, to understand what the speaker is trying to say. This is possible because we have "commonsense" concerning the word, which is built up from knowledge that is stored from long time experience. In order to understand the meaning, we think that the construction of a "Commonsense Judgment System" is necessary. Of the commonsense we use in our every day lives, one concerns the characteristics of words, such as an apple is red. This paper proposes a mechanism to associate the characteristics of a word based on our five senses with a knowledge base consisting of basic words. By using a concept-base, which is automatically constructed from dictionaries, this mechanism can understand a word that does not exist in the knowledge base. This study aims to retrieve the meaning concerning sense, and deepen semantic understanding.
展开▼