Proposal of a Method for Automated Extraction of Onomatopoeia in Regional Assembly Minutes

Abstract

An onomatopoeia is an useful linguistic expression to describe sounds, conditions, degrees and so on. Japanese has rich onomatopoeic expressions. They are frequently used in daily conversations. An onomatopoeia in a region may have a different meaning from one in different regions even if it is the same expression. Therefore, we attempt to investigate practical usage of onomatopoeias taken into account for the regional difference. However, general morphological analyzers cannot always recognize onomatopoeias. In this paper, we propose a method for automated extraction of onomatopoeias in regional assembly minutes. Although most previous work treats only four-letter onomatopoeias, our work treats not only four-letter onomatopoeias but also ones shorter than four letters.