법률상담 도메인의 자연어이해 모델 학습을 위한언어자원 구축 방법론
A Methodology for Building Linguistic Resources for Natural Language Understanding Model Training in a Legal Counseling Domain
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study proposes a methodology for constructing linguistic resources to train Natural Language Understanding (NLU) models for the legal counseling service. A dataset based on the language resources we propose is essential for developing non-face-to-face legal services that provide information related to legal problems. The linguistic resources were constructed through a bottom-up analysis of linguistic patterns of legal expressions, background descriptions, and discourse types in online legal counseling texts. Moreover, we analyzed the hierarchical classification of keywords in existing legal service systems and newly determined 20 keywords that belong to 4 representative legal categories. Local Grammar Graphs (LGGs), effective in describing local linguistic phenomena, were adopted to describe various linguistic patterns in this domain. These local language patterns, modularized in LGG format, are converted into Finite State Transducers (FSTs) and generate datasets required for training a language model for NLU. To evaluate this processing, we trained an NLU model of the open-source chatbot architecture Rasa with our dataset. The model performance shows a 0.91 f1-score, which affirms that the linguistic resources and the methodology proposed in this study can be practically applied in developing legal counseling chatbot systems.
Abstract
This study proposes a methodology for constructing linguistic resources to train Natural Language Understanding (NLU) models for the legal counseling service. A dataset based on the language resources we propose is essential for developing non-face-to-face legal services that provide information related to legal problems. The linguistic resources were constructed through a bottom-up analysis of linguistic patterns of legal expressions, background descriptions, and discourse types in online legal counseling texts. Moreover, we analyzed the hierarchical classification of keywords in existing legal service systems and newly determined 20 keywords that belong to 4 representative legal categories. Local Grammar Graphs (LGGs), effective in describing local linguistic phenomena, were adopted to describe various linguistic patterns in this domain. These local language patterns, modularized in LGG format, are converted into Finite State Transducers (FSTs) and generate datasets required for training a language model for NLU. To evaluate this processing, we trained an NLU model of the open-source chatbot architecture Rasa with our dataset. The model performance shows a 0.91 f1-score, which affirms that the linguistic resources and the methodology proposed in this study can be practically applied in developing legal counseling chatbot systems.
참고문헌 (19)
- 김도훈, "변호사의 업무상 인공지능 사용에 관한 소고 ― 미국변호사협회의 법조윤리모델규칙에 따른 윤리적 의무를 중심으로 ―", 미국헌법연구, 29(3), pp.241~272 (2018), 미국헌법학회
- 자질기반 감성분석(FbSA) 모델의 인공지능 학습을 위한 지식베이스-패턴문법 기반 반자동 학습데이터 증강(SSP) 방법 및 장치, "남지순", 한국외국어대학교 디코라 연구센터, ~, pp.DICORA-TR-2021-10 (2021)
- 박구락, "인공지능 기반의 법률상담 챗봇 시스템 개발", 한국컴퓨터정보학회논문지, 26(3), pp.29~34 (2021), 한국컴퓨터정보학회[DOI]
- 박동아, "인공지능 기반 대화형 공공 행정 챗봇 서비스에 관한 연구", 멀티미디어학회논문지, 20(8), pp.1347~1356 (2017), 한국멀티미디어학회[DOI]
- 박봉철, "법률상담 챗봇 정책을 위한 법률요건의 퍼지화 - 토지임차인의 건물매수청구권을 중심으로 -", 일감부동산법학, (21), pp.231~262 (2020), 법학연구소[DOI]
- 코로나19, 언택트 사회를 가속화하다, "배경임", 1~26, pp.이슈&진단 416 (2020)
- 양종모, "인공지능을 이용한 법률전문가 시스템의 동향 및 구상", 법학연구, 19(2), pp.213~242 (2016), 법학연구소
- 하미연, "Lawper 자연어 처리 기술을 통한 법률 상담 도우미 인공지능 챗봇 사업계획서", 석사, pp.2019
- Ahmed, I., "Based Voice Enabled Artificial Intelligent Chatterbot", International Journal of u-and e-Service, Science and Technology, 8(2), pp.375~384 (2015)[DOI]
- Bunk, T., "DIET: Lightweight Language Understanding for Dialogue Systems", ~ (2020)
- 최현준, "빈칸 되묻기 방식 기반 다중 키워드 처리가 가능한 주문용 챗봇 개발", 한국정보전자통신기술학회 논문지, 12(4), pp.440~448 (2019), 한국정보전자통신기술학회
- 최서원, "SW 교육 보조 도구로서의 AI 챗봇 활용", 한국정보통신학회논문지, 23(12), pp.1693~1699 (2019), 한국정보통신학회[DOI]
- Gross, M., "Finite-State Language Processing", pp.329~354 (1997), MIT Press
- Hu, T., "Study on the Influence of Artificial Intelligence on Legal Profession", 5th International Conference on Economics, Management, Law and Education, 110, pp.965~968 (2019)
- Liberatore, S., "Your AI Lawyer will See You Now: IBM’s ROSS Becomes World’s First Artificially Intelligent Attorney", Mail Online, ~ (2016)
- 박종렬, "AI 법률서비스에 관한 연구", 한국컴퓨터정보학회논문지, 23(7), pp.105~111 (2018), 한국컴퓨터정보학회[DOI]
- Popple, J., "Legal Expert Systems: The Inadequacy of a Rule-Based Approach", Australian Computer Science Communications, 12, pp.303~313 (1990)[DOI]
- Sharma, J. V., "An Intelligent Behaviour Shown by Chatbot System", International Journal of New Technology and Research, 3(4), pp.52~54 (2017)
- Weizenbaum, J, "ELIZA-a Computer Program for the Study of Natural Language Communication between Man and Machine", Communications of the ACM, 9(1), pp.36~45 (1966)[DOI]