RISS 학술연구정보서비스

검색

인기 검색어

    다국어 입력

    http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

    변환된 중국어를 복사하여 사용하시면 됩니다.

    예시)
    • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
    • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
    닫기

    언어의 계층적 구조를 이용한 한국어 영 대명사의 지시 해결 = Korean zero pronoun resolution using a hierarchical structure of language

    한글로보기

    https://www.riss.kr/link?id=T12892423

    • 저자
    • 발행사항

      대구 : 경북대학교 대학원, 2012

    • 학위논문사항

      학위논문 (박사) -- 경북대학교 대학원 , 컴퓨터공학과 , 2012. 8

    • 발행연도

      2012

    • 작성언어

      한국어

    • 주제어
    • DDC

      621.399 판사항(22)

    • 발행국(도시)

      대구

    • 형태사항

      vi, 110 p. : 삽화 ; 26 cm

    • 일반주기명

      참고문헌: p. 98-110

    • 소장기관
      • 경북대학교 중앙도서관 소장기관정보
      • 국립중앙도서관 국립중앙도서관 우편복사 서비스
    • 0

      상세조회
    • 0

      다운로드
    서지정보 열기
    • 내보내기
    • 내책장담기
    • 공유하기
    • 오류접수

    부가정보

    다국어 초록 (Multilingual Abstract) kakao i 다국어 번역

    In pro-drop languages such as Chinese, Japanese, and Korean,
    repetitive elements are easily omitted when they are inferable from the context.
    This phenomenon is commonly referred to as zero anaphora,
    and the omitted element is called as a zero pronoun (or zero anaphor).
    The resolution of zero pronouns is essential for natural language understanding,
    and thus is important for many NLP applications such as machine translation, information extraction, text summarization, question answering, and so on.

    One way to resolve zero pronouns is to pair each zero pronoun with the most plausible antecedent chosen from the antecedent candidates.
    That is, if a number of noun phrases precede a zero pronoun,
    the most plausible antecedent should be chosen from these noun phrases.
    Various kinds of features have been proposed to choose the most plausible antecedent, such as agreement feature, syntactic feature and structured feature.
    However, zero pronoun resolution is still difficult,
    no matter how nice are the features defined to choose the most plausible antecedent.
    This is because the number of antecedent candidates is generally very large,
    since a sentence has many noun phrases and all noun phrases preceding a zero pronoun can be its antecedent.
    This high cardinality of antecedent candidates is one of the major reasons which make zero pronoun resolution difficult.
    Therefore, a method to reduce this cardinality should be considered before defining the features to choose the most plausible antecedent.

    Languages are believed to have a hierarchy of linguistic units.
    On the basis of the hierarchy structure,
    candidate antecedents can be grouped into a larger unit such as phrase, clause, sentence, and paragraph.
    Since the number of clauses in a sentence is far less than that of phrases,
    it is easier, from the standpoint of the number of targets, to choose the clause with the antecedent of a zero pronoun than to find the antecedent directly.
    Therefore, this paper proposes a method for intra-sentential zero pronoun resolution by using clause-level antecedent identification.
    The proposed method first identifies the clause which may contain the antecedent for a given zero pronoun using structural information of clause.
    A parse tree kernel is adopted for modeling the structural information of clauses.
    Then, the antecedent of the zero pronoun is chosen from the noun phrases within the identified clause.
    If the first step is trustworthy enough,
    the proposed method outperforms other methods without the first step since the second step chooses the antecedent from far less number of candidates.

    Our experimental results show that the proposed method outperforms other methods without the first step,
    no matter what features are used to identify antecedents.
    This implies that the large norm of the candidate set is a major factor affecting the performance of zero pronoun resolution,
    and thus our two-step approach is more effective in resolving zero pronouns.
    In our future work, we intend to improve the first step of the identification of clauses further.
    The performance of zero anaphora resolution will be much better,
    if additional semantic information or a combination of structural and semantic features is used to identify the clause with antecedent.
    In addition, we plan to extend this approach to resolve zero pronouns which occur in various grammatical positions as well as to resolve inter-sentential zero pronouns.
    번역하기

    In pro-drop languages such as Chinese, Japanese, and Korean, repetitive elements are easily omitted when they are inferable from the context. This phenomenon is commonly referred to as zero anaphora, and the omitted element is called as a zero pron...

    In pro-drop languages such as Chinese, Japanese, and Korean,
    repetitive elements are easily omitted when they are inferable from the context.
    This phenomenon is commonly referred to as zero anaphora,
    and the omitted element is called as a zero pronoun (or zero anaphor).
    The resolution of zero pronouns is essential for natural language understanding,
    and thus is important for many NLP applications such as machine translation, information extraction, text summarization, question answering, and so on.

    One way to resolve zero pronouns is to pair each zero pronoun with the most plausible antecedent chosen from the antecedent candidates.
    That is, if a number of noun phrases precede a zero pronoun,
    the most plausible antecedent should be chosen from these noun phrases.
    Various kinds of features have been proposed to choose the most plausible antecedent, such as agreement feature, syntactic feature and structured feature.
    However, zero pronoun resolution is still difficult,
    no matter how nice are the features defined to choose the most plausible antecedent.
    This is because the number of antecedent candidates is generally very large,
    since a sentence has many noun phrases and all noun phrases preceding a zero pronoun can be its antecedent.
    This high cardinality of antecedent candidates is one of the major reasons which make zero pronoun resolution difficult.
    Therefore, a method to reduce this cardinality should be considered before defining the features to choose the most plausible antecedent.

    Languages are believed to have a hierarchy of linguistic units.
    On the basis of the hierarchy structure,
    candidate antecedents can be grouped into a larger unit such as phrase, clause, sentence, and paragraph.
    Since the number of clauses in a sentence is far less than that of phrases,
    it is easier, from the standpoint of the number of targets, to choose the clause with the antecedent of a zero pronoun than to find the antecedent directly.
    Therefore, this paper proposes a method for intra-sentential zero pronoun resolution by using clause-level antecedent identification.
    The proposed method first identifies the clause which may contain the antecedent for a given zero pronoun using structural information of clause.
    A parse tree kernel is adopted for modeling the structural information of clauses.
    Then, the antecedent of the zero pronoun is chosen from the noun phrases within the identified clause.
    If the first step is trustworthy enough,
    the proposed method outperforms other methods without the first step since the second step chooses the antecedent from far less number of candidates.

    Our experimental results show that the proposed method outperforms other methods without the first step,
    no matter what features are used to identify antecedents.
    This implies that the large norm of the candidate set is a major factor affecting the performance of zero pronoun resolution,
    and thus our two-step approach is more effective in resolving zero pronouns.
    In our future work, we intend to improve the first step of the identification of clauses further.
    The performance of zero anaphora resolution will be much better,
    if additional semantic information or a combination of structural and semantic features is used to identify the clause with antecedent.
    In addition, we plan to extend this approach to resolve zero pronouns which occur in various grammatical positions as well as to resolve inter-sentential zero pronouns.

    더보기

    목차 (Table of Contents)

    • 제1장 서 론 1
    • 1.1 연구 배경 1
    • 1.2 연구 내용 3
    • 1.3 논문의 기여와 구성 5
    • 제2장 관련 연구 8
    • 제1장 서 론 1
    • 1.1 연구 배경 1
    • 1.2 연구 내용 3
    • 1.3 논문의 기여와 구성 5
    • 제2장 관련 연구 8
    • 2.1 규칙-이론에 기반한 접근 방법 8
    • 2.2 기계 학습에 기반한 접근 방법 15
    • 2.3 영 대명사와 지시의 유형 23
    • 제3장 언어의 계층적 구조를 이용한 한국어 영 대명사의 지시 해결 28
    • 3.1 문제 정의 30
    • 3.2 다중 클래스 분류와 영 대명사의 지시 해결 32
    • 3.2.1 절 단계의 선행사 식별 38
    • 3.2.2 구 단계의 선행사 식별 45
    • 3.3 지시 해석을 위한 주석 달기 46
    • 3.3.1 한국어 구문구조 부착 말뭉치에 대한 간략한 소개 47
    • 3.3.2 지시 해석을 위한 주석 말뭉치 49
    • 제4장 영 대명사 지시 해결의 성능 평가 52
    • 4.1 실험 데이터 및 설정 52
    • 4.2 실험 결과 및 분석 55
    • 4.2.1 절 단계의 선행사 식별에 대한 결과 55
    • 4.2.2 문장 내 영 대명사의 지시 해결에 대한 성능 59
    • 제5장 절 단계의 선행사 식별에 대한 응용 69
    • 5.1 영 대명사의 문장 내 조응성 결정으로의 확장 69
    • 5.1.1 문장 내 조응성 결정에 대한 소개 69
    • 5.1.2 실험 및 결과 분석 73
    • 5.1.3 조응성 결정을 이용한 2 단계 영 대명사 지시 해결의 성능 74
    • 5.2 중심화 이론을 이용한 영 대명사 지시 해결로의 적용 78
    • 5.2.1 중심화 이론과 영 대명사의 지시 해결 78
    • 5.2.2 실험 및 결과 분석 81
    • 5.3 한 · 영 기계 번역을 위한 비지시적 영 대명사의 식별 82
    • 5.3.1 비지시적 영 대명사 식별의 중요성 83
    • 5.3.2 실험 및 결과 분석 86
    • 5.4 절 단계의 선행사 식별의 응용에 대한 결과 및 요약 90
    • 제6장 결 론 94
    • 참고 문헌 98
    • 초 록 111
    더보기

    분석정보

    View

    상세정보조회

    0

    Usage

    원문다운로드

    0

    대출신청

    0

    복사신청

    0

    EDDS신청

    0

    동일 주제 내 활용도 TOP

    더보기

    주제

    연도별 연구동향

    연도별 활용동향

    연관논문

    연구자 네트워크맵

    공동연구자 (7)

    유사연구자 (20) 활용도상위20명

    이 자료와 함께 이용한 RISS 자료

    나만을 위한 추천자료

    해외이동버튼