논문 상세보기

한국언어정보학회> 언어와 정보> 최소대립 문장쌍을 활용한 한국어 사전학습모델의 통사 연구 활용 가능성 검증

KCI등재

최소대립 문장쌍을 활용한 한국어 사전학습모델의 통사 연구 활용 가능성 검증

Verification of Korean Pre-trained Models' Feasibility of Syntactic Research Using Pairwise Sentences

박권식 ( Kwonsik Park ) , 김성태 ( Seongtae Kim ) , 송상헌 ( Sanghoun Song )
  • : 한국언어정보학회
  • : 언어와 정보 25권3호
  • : 연속간행물
  • : 2021년 11월
  • : 1-21(21pages)
언어와 정보

DOI

10.29403/LI.25.3.1


목차

1. 서론
2. 방법
3. 결과
4. 논의
5. 결론
<참고문헌>

키워드 보기


초록 보기

Syntactic studies make use of the minimally pairwise sentences as an argumentation tool, because the pairs allow us to pay attention to the constraints of interest. Likewise, it is helpful to use a set of minimal pairs in deep learning-based experiments for assessing the syntactic ability of neural language models. In this context, this study verifies whether the deep learning Korean model has the ability to properly distinguish the well-formed expressions and the corresponding ill-formed expressions. In the meanwhile, this study serves to examine the feasibility of the language resource constructed by the Korean government for deep learning architecture. The research is three-fold. First, we conducted an acceptability judgment testing to verify whether and how the language resource used in this study is indeed trustworthy. The results indicate that the judgments provided in the language resource converge with the judgments of our own experiment well enough. Second, we employed four Korean models such as mBERT, KoBERT, KR-BERT, KorBERT in order to evaluate how the language resource has a potentiality to predict the well-formedness of Korean expressions. The different models yield different results, the reason of which is fully discussed. Third, we made use of an independent test-set for evaluating the deep learning systems. It turns out that the results are still challenging, which implies that the current Korean models may have room for improvement to understand the syntactic phenomena.

UCI(KEPA)

I410-ECN-0102-2022-700-000822336

간행물정보

  • : 어문학분야  > 언어학
  • : KCI등재
  • :
  • : 연3회
  • : 1226-7430
  • :
  • : 학술지
  • : 연속간행물
  • : 1997-2021
  • : 318


저작권 안내

한국학술정보㈜의 모든 학술 자료는 각 학회 및 기관과 저작권 계약을 통해 제공하고 있습니다.

이에 본 자료를 상업적 이용, 무단 배포 등 불법적으로 이용할 시에는 저작권법 및 관계법령에 따른 책임을 질 수 있습니다.

25권3호(2021년 11월) 수록논문
최근 권호 논문
| | | |

KCI등재

1최소대립 문장쌍을 활용한 한국어 사전학습모델의 통사 연구 활용 가능성 검증

저자 : 박권식 ( Kwonsik Park ) , 김성태 ( Seongtae Kim ) , 송상헌 ( Sanghoun Song )

발행기관 : 한국언어정보학회 간행물 : 언어와 정보 25권 3호 발행 연도 : 2021 페이지 : pp. 1-21 (21 pages)

다운로드

(기관인증 필요)

초록보기

Syntactic studies make use of the minimally pairwise sentences as an argumentation tool, because the pairs allow us to pay attention to the constraints of interest. Likewise, it is helpful to use a set of minimal pairs in deep learning-based experiments for assessing the syntactic ability of neural language models. In this context, this study verifies whether the deep learning Korean model has the ability to properly distinguish the well-formed expressions and the corresponding ill-formed expressions. In the meanwhile, this study serves to examine the feasibility of the language resource constructed by the Korean government for deep learning architecture. The research is three-fold. First, we conducted an acceptability judgment testing to verify whether and how the language resource used in this study is indeed trustworthy. The results indicate that the judgments provided in the language resource converge with the judgments of our own experiment well enough. Second, we employed four Korean models such as mBERT, KoBERT, KR-BERT, KorBERT in order to evaluate how the language resource has a potentiality to predict the well-formedness of Korean expressions. The different models yield different results, the reason of which is fully discussed. Third, we made use of an independent test-set for evaluating the deep learning systems. It turns out that the results are still challenging, which implies that the current Korean models may have room for improvement to understand the syntactic phenomena.

KCI등재

2Negative Stripping in English: A Corpus-based Approach

저자 : Geonhee Lee , Jong-bok Kim

발행기관 : 한국언어정보학회 간행물 : 언어와 정보 25권 3호 발행 연도 : 2021 페이지 : pp. 23-42 (20 pages)

다운로드

(기관인증 필요)

초록보기

Stripping, also called bare argument ellipsis, is taken to be an elliptical construction that unexpresses everything from a clause except one constituent (e.g., Susan works at night, and Bill too.). It can also accompany the negator not, which we call Not-Stripping (e.g., Alan likes to play volleyball, but not Sandy.). This paper reviews key grammatical properties of Not-Stripping in English and investigates its authentic uses with the online corpus COCA (Corpus of Contemporary American English). The paper then performs some quantitative and qualitative research of the extracted data and discusses theoretical implications. The result from corpus investigation shows that Not-Stripping preferably used as PP remnant. Its register distribution also shows that Not-Stripping is most frequently used in fiction register followed by spoken, and magazine registers which may indicate that Not-Stripping is mainly used in colloquial context. In terms of category match/mismatch types, the construction is overtly used as mismatching relation between the remnant and the correlate. In addition, in case of merger/sprouting types, Not-Stripping seems to favor merger type, but sprouting type can be regarded as frequently used type. The grammatical function of both remnant and correlate are preferably used as modifier. The data for Not-Stripping are dealt with move-and-delete operations to postulate putative clausal source. Observing such attested data challenging the derivation of negative stripping from syntactic movement operations, the paper challenges a direct licensing construction-based analysis of the construction.

1
권호별 보기
같은 권호 다른 논문
| | | | 다운로드

KCI등재

1최소대립 문장쌍을 활용한 한국어 사전학습모델의 통사 연구 활용 가능성 검증

저자 : 박권식 ( Kwonsik Park ) , 김성태 ( Seongtae Kim ) , 송상헌 ( Sanghoun Song )

발행기관 : 한국언어정보학회 간행물 : 언어와 정보 25권 3호 발행 연도 : 2021 페이지 : pp. 1-21 (21 pages)

다운로드

(기관인증 필요)

초록보기

Syntactic studies make use of the minimally pairwise sentences as an argumentation tool, because the pairs allow us to pay attention to the constraints of interest. Likewise, it is helpful to use a set of minimal pairs in deep learning-based experiments for assessing the syntactic ability of neural language models. In this context, this study verifies whether the deep learning Korean model has the ability to properly distinguish the well-formed expressions and the corresponding ill-formed expressions. In the meanwhile, this study serves to examine the feasibility of the language resource constructed by the Korean government for deep learning architecture. The research is three-fold. First, we conducted an acceptability judgment testing to verify whether and how the language resource used in this study is indeed trustworthy. The results indicate that the judgments provided in the language resource converge with the judgments of our own experiment well enough. Second, we employed four Korean models such as mBERT, KoBERT, KR-BERT, KorBERT in order to evaluate how the language resource has a potentiality to predict the well-formedness of Korean expressions. The different models yield different results, the reason of which is fully discussed. Third, we made use of an independent test-set for evaluating the deep learning systems. It turns out that the results are still challenging, which implies that the current Korean models may have room for improvement to understand the syntactic phenomena.

KCI등재

2Negative Stripping in English: A Corpus-based Approach

저자 : Geonhee Lee , Jong-bok Kim

발행기관 : 한국언어정보학회 간행물 : 언어와 정보 25권 3호 발행 연도 : 2021 페이지 : pp. 23-42 (20 pages)

다운로드

(기관인증 필요)

초록보기

Stripping, also called bare argument ellipsis, is taken to be an elliptical construction that unexpresses everything from a clause except one constituent (e.g., Susan works at night, and Bill too.). It can also accompany the negator not, which we call Not-Stripping (e.g., Alan likes to play volleyball, but not Sandy.). This paper reviews key grammatical properties of Not-Stripping in English and investigates its authentic uses with the online corpus COCA (Corpus of Contemporary American English). The paper then performs some quantitative and qualitative research of the extracted data and discusses theoretical implications. The result from corpus investigation shows that Not-Stripping preferably used as PP remnant. Its register distribution also shows that Not-Stripping is most frequently used in fiction register followed by spoken, and magazine registers which may indicate that Not-Stripping is mainly used in colloquial context. In terms of category match/mismatch types, the construction is overtly used as mismatching relation between the remnant and the correlate. In addition, in case of merger/sprouting types, Not-Stripping seems to favor merger type, but sprouting type can be regarded as frequently used type. The grammatical function of both remnant and correlate are preferably used as modifier. The data for Not-Stripping are dealt with move-and-delete operations to postulate putative clausal source. Observing such attested data challenging the derivation of negative stripping from syntactic movement operations, the paper challenges a direct licensing construction-based analysis of the construction.

1
주제별 간행물
간행물명 최신권호

KCI등재

일본어문학
93권 0호

KCI등재

텍스트언어학
52권 0호

KCI등재

이중언어학
88권 0호

KCI등재

언어와 문화
18권 2호

KCI등재

Journal of Korean Culture (JKC)
57권 0호

KCI등재

중국학연구
100권 0호

KCI등재

외국어교육연구
36권 2호

KCI등재

언어연구
38권 1호

KCI등재

한국어문교육
39권 0호

KCI등재

이중언어학
87권 0호

KCI등재

언어와 언어학
96권 0호

KCI등재

한국언어문화
77권 0호

KCI등재

기호학 연구
70권 0호

KCI등재

언어학
30권 1호

KCI등재

언어와 정보사회
45권 0호

KCI등재

국어교육학연구
57권 1호

KCI등재 SCOUPUS

언어연구
39권 1호

KCI등재

일본어문학
92권 0호

KCI등재

이중언어학
86권 0호

KCI등재

Journal of Korean Culture (JKC)
56권 0호
발행기관 최신논문
자료제공: 네이버학술정보
발행기관 최신논문
자료제공: 네이버학술정보

내가 찾은 최근 검색어

최근 열람 자료

맞춤 논문

보관함

내 보관함
공유한 보관함

1:1문의

닫기