서브메뉴
검색
Language Change in Ancient Chinese: A Computational Approach
Language Change in Ancient Chinese: A Computational Approach
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202104721
- ISBN
- 9798288880940
- DDC
- 401
- 저자명
- Tian, Zuoyu.
- 서명/저자
- Language Change in Ancient Chinese: A Computational Approach
- 발행사항
- [Sl] : Indiana University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 221 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-01, Section: A.
- 주기사항
- Advisor: Kubler, Sandra;Amaral, Patricia.
- 학위논문주기
- Thesis (Ph.D.)--Indiana University, 2025.
- 초록/해제
- 요약This dissertation employs computational methods to investigate language change in Ancient Chinese from the Tang to Qing dynasties, with a particular focus on language periodization. Traditional approaches to Chinese periodization rely heavily on close reading of historical texts which demands extensive expertise. Recent computational studies have tried to predict text dynasties using automated systems, yet these efforts prioritize classification model design and benchmark creation over linguistic analysis. To address this gap, I introduce a new diachronic corpus of Biji (笔记, "written notes"), which is rich in conversational language and covers diverse topics, along with an additional dataset of Chinese Buddhist conversations to test model robustness. First, I evaluate different feature representation methods, character/word n-grams, static embeddings, and contextualized embeddings, on the Biji corpus. The results indicate that the task is very challenging, with contextualized embeddings (especially when used with SVM classifiers) delivering superior performance. Next, I examine model generalization on out-of-domain data and explore improvements via contrastive learning, which yields marginal gains in both in-domain and out-of-domain experiments. Finally, by conducting a neighboring dynasty classification, I reveal that distinguishing texts from the Ming and Qing dynasties is particularly difficult, suggesting they may belong to the same language period, and identify lexical change, such as changes in bureaucratic terminology and semantic narrowing.
- 일반주제명
- Linguistics
- 일반주제명
- Religion
- 일반주제명
- Ancient languages
- 기타저자
- Indiana University Linguistics
- 기본자료저록
- Dissertations Abstracts International. 87-01A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017358574
■00520260202104721
■006m o d
■007cr#unu||||||||
■020 ▼a9798288880940
■035 ▼a(MiAaPQ)AAI32121467
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a401
■1001 ▼aTian, Zuoyu.
■24510▼aLanguage Change in Ancient Chinese: A Computational Approach
■260 ▼a[Sl]▼bIndiana University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a221 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-01, Section: A.
■500 ▼aAdvisor: Kubler, Sandra;Amaral, Patricia.
■5021 ▼aThesis (Ph.D.)--Indiana University, 2025.
■520 ▼aThis dissertation employs computational methods to investigate language change in Ancient Chinese from the Tang to Qing dynasties, with a particular focus on language periodization. Traditional approaches to Chinese periodization rely heavily on close reading of historical texts which demands extensive expertise. Recent computational studies have tried to predict text dynasties using automated systems, yet these efforts prioritize classification model design and benchmark creation over linguistic analysis. To address this gap, I introduce a new diachronic corpus of Biji (笔记, "written notes"), which is rich in conversational language and covers diverse topics, along with an additional dataset of Chinese Buddhist conversations to test model robustness. First, I evaluate different feature representation methods, character/word n-grams, static embeddings, and contextualized embeddings, on the Biji corpus. The results indicate that the task is very challenging, with contextualized embeddings (especially when used with SVM classifiers) delivering superior performance. Next, I examine model generalization on out-of-domain data and explore improvements via contrastive learning, which yields marginal gains in both in-domain and out-of-domain experiments. Finally, by conducting a neighboring dynasty classification, I reveal that distinguishing texts from the Ming and Qing dynasties is particularly difficult, suggesting they may belong to the same language period, and identify lexical change, such as changes in bureaucratic terminology and semantic narrowing.
■590 ▼aSchool code: 0093.
■650 4▼aLinguistics
■650 4▼aReligion
■650 4▼aAncient languages
■653 ▼aChinese periodization
■653 ▼aSemantic narrowing
■653 ▼aBureaucratic terminology
■653 ▼aChinese Buddhist conversations
■690 ▼a0290
■690 ▼a0289
■690 ▼a0318
■71020▼aIndiana University▼bLinguistics.
■7730 ▼tDissertations Abstracts International▼g87-01A.
■790 ▼a0093
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358574▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
