영어 말하기 자동채점의 현재와 미래
The present and future of an automated scoring program for speaking skills of English.
0
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
The present study aims at developing an automated scoring program for assessing Koreanstudents’ English speaking ability. Building on the prototype English speaking automatedscoring program developed in 2012, this study had the following three goals in mind: First, theperformance of the prototype speaking automated scoring program needs to be improved byenhancing the recognition rate of the speech recognition system embedded in the automatedscoring program. Second, the algorithm of the automated scoring program needs to beimproved by refining the existing pool of scoring features. Third, the performance of themodified automated scoring program needs to be validated in order to explore the possibilityof applying the program to the classroom. For this, two different types of algorithms, called theMaximum Entropy (ME) and Multiple Regression (MR), were used to apply the scoringfeatures and analyze the performances of scoring models. The results showed that MR isslightly more efficient and reliable compared with ME. The automated scoring program stillhas a long way to go, but it certainly has a place in speaking assessments especially whenconsidering its potential for not only an assessment tool but also a learning tool for students.
Abstract
The present study aims at developing an automated scoring program for assessing Koreanstudents’ English speaking ability. Building on the prototype English speaking automatedscoring program developed in 2012, this study had the following three goals in mind: First, theperformance of the prototype speaking automated scoring program needs to be improved byenhancing the recognition rate of the speech recognition system embedded in the automatedscoring program. Second, the algorithm of the automated scoring program needs to beimproved by refining the existing pool of scoring features. Third, the performance of themodified automated scoring program needs to be validated in order to explore the possibilityof applying the program to the classroom. For this, two different types of algorithms, called theMaximum Entropy (ME) and Multiple Regression (MR), were used to apply the scoringfeatures and analyze the performances of scoring models. The results showed that MR isslightly more efficient and reliable compared with ME. The automated scoring program stillhas a long way to go, but it certainly has a place in speaking assessments especially whenconsidering its potential for not only an assessment tool but also a learning tool for students.
참고문헌 (12)
- 권서경, "EBS 연계정책에 따른 대학수학능력시험 영어영역 어휘 난이도 변화 분석", 영어교과교육, 13(4), pp.97~121 (2014), 한국영어교과교육학회[DOI]
- 국가영어능력평가 시험 말하기 자동채점 프로그램 개발, "박태준", 한국교육과정평가원, ~, pp.한국교육과정평가원 연구보고 RRE 2013-14 (2013)
- 국가영어능력평가시험의 말하기 자동채점 프로그램 도입 방안, "신동광", 한국교육과정평가원, ~, pp.한국교육과정평가원 연구보고 RRE 2012-9 (2012)
- 이용상, "쓰기 자동채점 알고리듬의 성능 비교_최대 엔트로피 기법과 서포트 벡터 회귀 기법", 교육과정평가연구, 16(3), pp.147~165 (2013), 한국교육과정평가원
- 서답형 문항 자동 채점 프로그램 도입 방안 연구(Ⅰ), "진경애", 한국교육과정평가원, ~, pp.한국교육과정평가원 연구보고 RRI 2006-6 (2006)
- 서답형 문항 자동채점 프로그램 도입 방안 연구(Ⅱ), "진경애", 한국교육과정평가원, ~, pp.한국교육과정평가원 연구보고 RRE 2007-4 (2007)
- KICE - Pearson 영어 말하기, 쓰기 자동채점 프로그램 타당성 연구, "진경애", 한국교육과정평가원, ~ (2011)
- Higgins, D., "A three-stage approach to the automated scoring of spontaneous spoken responses", Computer Speech & Language, 25(2), pp.282~306 (2011)
- Jeon, J., "Acoustic feature-based non-scorable response detection for an automated speaking proficiency assessment", 13th Annual Conference of the International Speech Communication Associatio (2012)
- "VersantTM Junior English Test-Level 1: Test description and validation summary" (2011)[URL]
- Xi, X., "A comparison of two scoring methods for an automated speech scoring system", Language Testing, 29(3), pp.371~394 (2012)
- Zechner, K., "Automatic scoring of non-native spontaneous speech in tests of spoken English", Speech Communication, 51, pp.883~895 (2009)