AI 어시스턴트의 요청문 인식 및 분류 주석을 위한 음악청취 관련 문형 패턴 연구
A Study on Music-request Sentence Patterns in AI-assistant Platforms for the Automatic Classification and Annotation of Requests
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
This study aims to describe music-related request patterns observed in AI assistant platforms and formalize them by using the local grammar graph(LGG) methodology. These patterns, transformed into Finite-State Transducers in the Unitex platform, allow us to automatically classify and annotate various sentences used for request, which is crucial for diverse machine learning approaches. In this study, we examined a corpus of tweet texts crawled by Deco-T-Crawler as seed data and classified music-related requests into 3 categories: music on/off, volume up/down and music-play control. Then each category was divided into sub-categories which were represented by several LGGs. By applying these LGGs and the DECO Korean dictionary on test data, we obtained the information retrieval performance. In this regard, the linguistic resources proposed in this study are proved concrete and meaningful
Abstract
This study aims to describe music-related request patterns observed in AI assistant platforms and formalize them by using the local grammar graph(LGG) methodology. These patterns, transformed into Finite-State Transducers in the Unitex platform, allow us to automatically classify and annotate various sentences used for request, which is crucial for diverse machine learning approaches. In this study, we examined a corpus of tweet texts crawled by Deco-T-Crawler as seed data and classified music-related requests into 3 categories: music on/off, volume up/down and music-play control. Then each category was divided into sub-categories which were represented by several LGGs. By applying these LGGs and the DECO Korean dictionary on test data, we obtained the information retrieval performance. In this regard, the linguistic resources proposed in this study are proved concrete and meaningful
참고문헌 (18)
- 고대영, "화행과 요청", 배달말, (55), pp.1~23 (2014), 배달말학회
- "아마존·구글의 ‘AI 생태계 장악’ 눈으로 확인한 CES (Amazon and Google's Domination of AI Ecosystem Confirmed in CES)" (2019)[URL]
- 남지순, "코퍼스 분석을 위한 한국어 전자사전 구축방법론 (An Introduction to a Methodology of Implementing Korean Electronic Dictionaries for Corpus Analysis)" (2018), 출판사 역락 (Youkrak)
- 류승희, "콘텐츠 스트리밍 산업의 성장동력화가 시급하다: ICT와의 결합으로 커지는 콘텐츠시장 (An Urgent Need for Growth Engines in the Content Streaming Industry)", 한국경제주평 (Weekly Economic Review), 829, pp.1~16 (2019)
- "뜨거운 AI 스피커 시장, 차가운 소비자 평가 (Hot AI Speaker Market, Cold Consumer Evaluation)" (2018)[URL]
- 박수아, "인공지능 스피커 만족도와 지속적 이용의도에 영향을 미치는 요인: 기능적, 정서적 요인을 중심으로", 정보사회와 미디어, 19(3), pp.159~182 (2018), 한국정보사회학회[DOI]
- "구글홈 온다…AI스피커시장 판 흔들까 (Google Home is Coming)" (2018)[URL]
- 이민우, "유의어의 의미 사용 양상 분석", 언어학 연구, (44), pp.135~154 (2017), 한국중원언어학회[DOI]
- 이준희, "명령문의 간접 화행 (Indirect Speechacts of Imperative Sentence)", 한국어 의미학 (Korean Semantics), 8, pp.279~290 (2001)
- 이지수, "한국어 명령문의 조건과 범위", 國語學, (75), pp.233~270 (2015), 국어학회[DOI]
- 조민하, "구어 의문문 어미의 문법성과 화용성 -여성 자유발화의 억양 분석을 통하여-", 한국어 의미학, 52, pp.61~85 (2016), 한국어의미학회[DOI]
- 인공지능(AI) 가전제품 문제점 및 개선방안 (AI Home Appliance Problems and Solutions), "강민영", 한국소비자원 (Korean Consumer Agency), 1~33 (2017)
- 황성수, "신경망 기반 언어모델의 연구 동향 (Research Trends of Neural Network-based Language Models)", 한국통신학회지 (The Journal of The Korean Institute of Communication Sciences), 35(12), pp.22~28 (2018)
- SNS 사용자 생성문에 대한 코퍼스 수집 시스템 구축 방법론: Deco Crawlers (Introducing Deco Crawling Systems for Collecting User-generated Sentences in Social Network Services: Deco Crawlers), "황창회", 한국외국어대학교 DICORA 연구센터 (DICORA Research Center in HUFS), ~, pp.DICORA-TR-01-2018 (2018)
- Gross, M., "Finite-State Language Processing", pp.329~354 (1997), the MIT Press
- Gross, M, "Nouvelles Applications des Graphes D’automates Finis a la Description Linguistique", Lingvisticae Investigationes, 22(1-2), pp.249~262 (1999)
- Paumier, S, "De la Reconnaissance de Formes Linguistiques a L’analyse Syntaxique", Ph. D, pp.2003
- Wang, Y., "A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling", Proceeding of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics, pp.309~314 (2018)