Host: The Japanese Society for Artificial Intelligence
Name : The 36th Annual Conference of the Japanese Society for Artificial Intelligence
Number : 36
Location : [in Japanese]
Date : June 14, 2022 - June 17, 2022
Currently, we need to prepare structured medical information for an aging society. The range of medical information is not limited to medical terminology dictionaries and teaching materials, but also covers a wide range of fields such as nursing records, electronic medical records, and postings on SNS. Researches such as text mining and information extraction using the medical information secondarily has become particularly active. In this research, we have two aproaches. First one is analyzing medical terms by adding vocabulary, usage, and context level information. Second one is setting the learning difficulty level from the viewpoint of vocabulary, learning frequency, and explanatory based on the structured data. The purpose of this study is to verify its effectiveness. In this paper, we collected nursing textbooks as data, extracted medical terms, and calculated the frequency of appearance. We extracted and compared using the compound words, word components, and semantic labels included in "Practical medical terms Word component Lexicon Ver.1.0". Based on this result, we consider essential elements for structuring medical terms.
