피부질환 의료상담 챗봇 구현을 위한사용자 질의문 패턴분석 연구
An Analysis of Linguistic Patterns in User Queries for Implementation of Medical Chatbots in Skin Disease Counseling Domain
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This research delves into linguistic patterns within a medical QA corpus focused on skin diseases. Our primary goal is to analyze these patterns and establish linguistic resources for the automated extraction of diagnostic information, notably disease and symptom expressions. A thorough examination of the corpus revealed three key linguistic patterns in user utterances: varied disease and symptom descriptions, specific query-related linguistic structures, and expressions giving supplementary background information. From these patterns, we classified 12 distinct query types. Furthermore, we identified three vital query-related expressions concerning skin diseases: WHAT, WHY, and HOW-CURE. These linguistic patterns were encapsulated using the Local Grammar Graph (LGG) schema, designed to efficiently produce training datasets for medical chatbots' Natural Language Understanding (NLU) modules. Validating our approach, a medical counseling chatbot named LIMA, trained using our dataset, achieved an F1-score of 0.908, underscoring the effectiveness and reliability of our proposed method.
Abstract
This research delves into linguistic patterns within a medical QA corpus focused on skin diseases. Our primary goal is to analyze these patterns and establish linguistic resources for the automated extraction of diagnostic information, notably disease and symptom expressions. A thorough examination of the corpus revealed three key linguistic patterns in user utterances: varied disease and symptom descriptions, specific query-related linguistic structures, and expressions giving supplementary background information. From these patterns, we classified 12 distinct query types. Furthermore, we identified three vital query-related expressions concerning skin diseases: WHAT, WHY, and HOW-CURE. These linguistic patterns were encapsulated using the Local Grammar Graph (LGG) schema, designed to efficiently produce training datasets for medical chatbots' Natural Language Understanding (NLU) modules. Validating our approach, a medical counseling chatbot named LIMA, trained using our dataset, achieved an F1-score of 0.908, underscoring the effectiveness and reliability of our proposed method.
참고문헌 (27)
- 강정석, "챗봇을 활용한 전문의료상담 및 예약플랫픔 “헬스챗”", 한국정보처리학회 학술대회논문집, 24(2), pp.778~780 (2017)
- 김상균, "한의 온톨로지 기반 시맨틱 검색 시스템", 한국콘텐츠학회 논문지, 12(12), pp.533~543 (2012), 한국콘텐츠학회[DOI]
- 김준희, "국어의 통증 표현 연구", 한말연구, (52), pp.81~109 (2019), 한말연구학회[DOI]
- 비대면 시대, 비대면 의료 국내외 현황과 발전, "김지연", 한국과학기술기획평가원, ~ (2020)
- 김혜은, "한의학 증상용어의 형태소 분석을 위한 자연어 표기 분석", 대한예방한의학회지, 17(2), pp.179~187 (2013), 대한예방한의학회
- 금융앱 챗봇의 사용자 의도 분석 모델 개발을 위한 학습데이터 이중 증강 방법, "남지순", 한국외국어대학교 디코라연구센터, ~, pp.DICORA-TR-2021-12 (2021)
- 류연준, "인공지능 챗봇을 기반으로 한 환자-의사소통소프트웨어", 한국정보처리학회 학술대회논문집, 2, pp.501~504 (2020)
- 이상백, "전문용어 정제를 위한 형태소 분석을 이용한 한의학 증상 진단 시스템 개발", 정보과학회 컴퓨팅의 실제 논문지, 22(2), pp.77~82 (2016), 한국정보과학회
- 피부과 증상상담 챗봇 LIMA 구현을 위한 언어자원 연구, "이윤우", 한국외국어대학교 디코라연구센터, ~, pp.DICORA-TR-2022-05 (2022)
- 장윤희, "119 구급 신고 전화의 한국어 증상 표현 연구", 한국화재소방학회 논문지, 30(4), pp.135~140 (2016), 한국화재소방학회[DOI]
- 장호, "자연어 기술 기반 한의 증상명 추천 시스템 (소화기계 질환 버전)", 한국지식정보기술학회 논문지, 15(5), pp.831~843 (2020), 한국지식정보기술학회[DOI]
- 홍유식, "휴대폰을 이용한 지능형 의료진단 시스템", 한국인터넷방송통신학회 논문지, 11(2), pp.213~218 (2011), 한국인터넷방송통신학회
- 황주성, "통증 어휘에 따른 통증 종류와 강도 간의 관련성", 대한물리치료과학회지, 22(1), pp.29~36 (2015)
- Blanc, C., "FlauBERT vs. CamemBERT: Understanding Patient's Answers by a French Medical Chatbot", Artificial Intelligence in Medicine, 127 (2022)
- Gogia, S., "Fundamentals of Telemedicine and Telehealth" (2020), Academic Press
- Gross, M., "Finite-State Language Processing", pp.329~354 (1997), MIT Press
- Hu, E. J., "Lora : Low-rank Adaptation of Large Language Models", arXiv preprint arXiv:2106.09685, ~ (2021)
- Hwang, M., "KoRasa : Pipeline Optimization for Open-Source Korean Natural Language Understanding Framework Based on Deep Learning", Mobile Information Systems, 9 (2021)
- Kaplan, J., "Scaling Laws for Neural Language Models", CoRR (2020)
- Young-Min Kim, "Korean clinical entity recognition from diagnosis text using BERT", BMC Medical Informatics and Decision Making, 20(S7) (2020), Springer Science and Business Media LLC[DOI]
- Kim, Y., "Predicting Medical Specialty from Text based on a Domain-specific Pre-trained BERT", International Journal of Medical Informatics, 170, pp.104956~ (2023)
- Paumier, S., "Unitex Users’ Manual" (2003), UPEM
- Rosruen, N., "Chatbot utilization for medical consultant system", Proceedings of 3rd Technology Innovation Management and Engineering Science International Conference (TIMES-iCON), pp.1~5 (2018)
- Tamizharasi, B., "Building a Medical Chatbot using Support Vector Machine Learning Algorithm", Journal of Physics: Conference Series, 1716(1) (2020)
- Weizenbaum, J., "ELIZA—a Computer Program for the Study of Natural Language Communication between Man and Machine", Communication of the Association for Computing Machinery, 9, pp.36~45 (1966)
- Yu, T., "SeqGPT : An Out-of-the-box Large Language Model for Open Domain Sequence Understanding", arXiv preprint arXiv : 2308, ~ (2023)
- Brown, Tom B., "Language Models are Few-Shot Learners", Advances in Neural Information Processing Systems, 33, pp.1877~1901 (2020)