개체명인식과 서브워드 임베딩 기술을 활용한 건강 문서 검색 시스템

Abstract

Due to the growth of the healthcare service andthe global epidemic, the demand for personalhealth-related services is increasing, and theseservices are provided to consumers through Q&Asystems. Most Q&A systems are keyword-basedsystems that allow users to search for desiredcontent only when they know the exact words ofthe disease. However, users lack health knowledge,so when searching, they enter queries inabbreviations and typos, not exact names of words.This results in a drop in the performance ofkeyword-based Q&A systems. In this paper, wepropose a Korean-based health document retrieval system that can recognize various terms of healthquestions that are entered from users exploitingnamed entity recognition and subword embeddingtechniques.