19세기 문헌 국역본의 개체명 인식 및 관계 추출을 위한 기초 연구
Named Entity Detection and Relation Extraction in the Personal Chronology of the 19th Century
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
This study aims at exploring the methodology in named entity detection and its relational extraction in the personal chronobiology of Myun-am, scholar and politician in the late 19th century. Using ACE tagging tool to annotate the named entities, such as person's name, organization, and the location, we examine the applicability of the ACE tool in order to build a knowledge base from the unstructured data. We propose to import the wordnet's ontology in order to establish the sub-categories of the [PER] relation and acquire semantic attributes. We argue that the ACE tag set should be modified and sub-categorized and propose the new categories acquired from the text. Additionally, we argue that using the existing large scale lexical resources like Korean wordnet(KorLex 1.5) can partially provide the semantic attributes to the templates relation.
Abstract
This study aims at exploring the methodology in named entity detection and its relational extraction in the personal chronobiology of Myun-am, scholar and politician in the late 19th century. Using ACE tagging tool to annotate the named entities, such as person's name, organization, and the location, we examine the applicability of the ACE tool in order to build a knowledge base from the unstructured data. We propose to import the wordnet's ontology in order to establish the sub-categories of the [PER] relation and acquire semantic attributes. We argue that the ACE tag set should be modified and sub-categorized and propose the new categories acquired from the text. Additionally, we argue that using the existing large scale lexical resources like Korean wordnet(KorLex 1.5) can partially provide the semantic attributes to the templates relation.
참고문헌 (12)
- 왕지현, "인물 백과사전 지식베이스 구축을 위한 속성패턴기반 정보추출", 한국정보과학회 가을 학술발표논문집, 31(2), pp.793~795 (2004)
- 윤애선, "한국어 어휘의미망 ｢KorLex 1.5｣의 구축", 정보과학회논문지 : 소프트웨어 및 응용, 36(1), pp.92~108 (2009), 한국정보과학회
- Agichtein, E., "Analysis of Factoid Questions for Effective Relation Extraction" (2005), SIGIR
- An, J., "Automatic acquisition of Named Entity tagged corpus from World Wide Web", Proceedings of the 41st annual meeting of the ACL (2003)
- Byrne, K., "Nested Named Entity Recognition in Historical Archive Text", Interntional Conference on Semantic Computing (2007), IEEE
- Chung, E., "Korean Named Entity Recognition using HMM and CoTraining Model", Proceedings of the 6th International Workshop on Information Retrieval with Asian Language, pp.161~167 (2003)
- Lee,C.and al, "Fine-Grained Named Entity Recognition Using Conditional Random Fields for Question Answering, AIRS", LNCS, 4182, pp.581~587 (2006)
- Lee, C., "Fine-Grained Named Entity Recognition and Relation Extraction for Question Answering", PROCEEDINGS OF THE ANNUAL INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 30(2007) (2007)
- Fleischman, M., "Fine grained classification of named entities", COLING 2002 (2002)
- A LF based Answer Indexing Method for Encyclopedia Question Answering System, "Kim, H.", AIRS, ~ (2004)
- The Evaluation Plan for the ACE 2007, "NIST", Pilot Evaluation of Entity Translation, ~ (2007)
- "Named Entity: History and Future"[URL]