A study on the improvement of the model for Korean semantic role description: Focusing on the structural improvement of the Korean PropBank framefiles

Seoin Shin

doi:10.19033/sks.2020.12.70.269

The purpose of this paper is to analyze the structure of the Korean PropBank framefiles and suggest several ways to improve it. In the paper, we discuss the features and limitations of the Korean PropBank framefiles and propose an alternative model for semantic role description. In terms of macro structure, the Korean PropBank framefiles have a peculiar structure. The lemma representing several words becomes the entry, and the related vocabulary is described in one file. Therefore, the lemma setting criteria and related vocabulary processing criteria should be clearly established, and homonyms should be processed in a consistent way. In terms of micro structure, there is no place in the Korean PropBank framefiles to describe postposition(josa) information, which is essential for Korean semantic role labeling. Therefore, this lack has to be supplemented. In describing the sematic role information, it is more useful to describe it as a label-type sematic role rather than as a number-type sematic role or a narrative-type sematic role. In the Korean PropBank framefiles, arguments and adjuncts are analyzed in different ways in the analysis of example sentence, but they need to be analyzed parallelly. In order to take care of the suggestions for improvement, we propose an alternative model for Korean semantic role description. This new model will be able to describe information that is useful for a more effective analysis of Korean semantic role.

Citation status

KCI Citation Counts (1)
열림/닫힘 버튼
REFERENCES (20)
열림/닫힘 버튼
* 2021년 이후 발행 논문의 참고문헌은 현재 구축 중입니다.

[journal] 김윤정 / 2014 / Consideration of Sematic Roles of Korean Subcategory in Computational Linguistics / 언어와 정보 / 한국언어정보학회 18(2) : 169~199

[journal] 김윤정 / 2016 / Consideration of various problems of Sematic Roles Tagging / 언어와 정보 / 한국언어정보학회 20(2) : 1~26

[journal] 박철우 / 2005 / Le système des rles sémantiques et son inventaire conçus pour la description sémantique des verbes et des adjectifs coréens / 어학연구 / 언어교육원 41(3) : 543~568

[confproc] 박태호 / 2017 / 형태의미정보를 이용한 한국어 의미역 결정 / 한국정보과학회학술발표논문집 2017(6) : 590~592

[journal] 배장성 / 2015 / Extending Korean PropBank for Korean Semantic Role Labeling and Applying Domain Adaptation Technique / 인지과학 / 한국인지과학회 26(4) : 377~392 / 10.19066/cogsci.2015.26.4.001

[journal] 배장성 / 2017 / Korean Semantic Role Labeling using Stacked Bidirectional LSTM-CRFs / 정보과학회논문지 / 한국정보과학회 44(1) : 36~43

[journal] 신서인 / 2019 / A study on the semantic role labels for the construction of a sematic role annotated Korean corpus / 한국어 의미학 / 한국어의미학회 66 : 175~204

[book] 이선웅 / 2019 / 의미역 기술 모형 연구 및 시범 구축 / 국립국어원

[journal] 이숙의 / 2018 / Automatic Processing of Predicative Nouns for Korean Semantic Recognition. / 한국어학 / 한국어학회 80 : 151~175 / http://dx.doi.org/10.20405/kl.2018.08.80.151

[journal] 이숙의 / 2020 / On the semantic role of adjuncts for the descriptive QA system / 한국어 의미학 / 한국어의미학회 69 : 1~24

[journal] 이홍식 / 2019 / 의미역의 분류에 대하여 / 한국어와 문화 / 숙명여자대학교 한국어문화연구소 26 : 95~120

[journal] 이홍식 / 2020 / On the Semantic Roles of Double Subject Constructions / 비교문화연구 / 비교문화연구소 59 : 293~326 / 10.21049/ccs.2020.59..293

[report] 임수종 / 2018 / 한국어 의존의미역 태깅 가이드라인 / 한국전자통신연구원

[journal] 조정현 / 2012 / A Development of the Automatic Predicate-Argument Analyzer for Construction of Semantically Tagged Korean Corpus / 정보처리학회논문지. 소프트웨어 및 데이터 공학 / 한국정보처리학회 19(1) : 43~52

[journal] 최형강 / 2019 / Thematic Roles of ‘lo’ Phrase - Focusing on EFF, INS, FNS - / 인문연구 / 인문과학연구소 (88) : 115~144

[journal] 최형강 / 2020 / A Study on Korean PropBank: Focus on <roleset> and <lemma> / 한국어학 / 한국어학회 88 : 247~273 / http://dx.doi.org/10.20405/kl.2020.08.88.247

[report] 홍재성 / 2003 / 21세기 세종계획 전자사전 개발 분과 연구보고서 / 문화관광부·국립국어연구원

[web] Palmer, Martha / Korean Propbank / http://catalog.ldc.upenn.edu/LDC2006T03

[report] Bonial / 2012 / English PropBank Annotation Guidelines / University of Colorado at Boulder

[report] Bonial / 2010 / PropBank Annotation Guidelines / University of Colorado at Boulder

KJC Korea
Journal Central

Statistics

Tools

Sharing

Issue List

Citation status