서브메뉴
검색
Understanding, Building, and Evaluating Models for Context Aware Conditional Natural Language Generation
Understanding, Building, and Evaluating Models for Context Aware Conditional Natural Language Generation
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151151
- ISBN
- 9798384447702
- DDC
- 616.8
- 저자명
- Chan, David M.
- 서명/저자
- Understanding, Building, and Evaluating Models for Context Aware Conditional Natural Language Generation
- 발행사항
- [Sl] : University of California, Berkeley, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 252 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
- 주기사항
- Advisor: Canny, John.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Berkeley, 2024.
- 초록/해제
- 요약If you ask a human to describe an image, they might do so in a thousand different ways. Each of these descriptions depends not only on the image but also on a rich tapestry of contextual hints and clues surrounding the image (up to and including the person doing the describing themselves). Until now, the field of conditional natural language generation has focused almost solely on the perception component of the task: how do we perceive what is in the stimulus -- be it audio, visual, or textual -- and relay it to the user? In this dissertation, we argue that models that focus solely on the stimulus (and not the associated context) suffer significant shortcomings in their ability to generate language that aligns well with human judgments of quality and content while decreasing their overall utility for downstream tasks. This dissertation focuses on three core objectives in the pursuit of building a context-aware conditional natural language generation (CNLG) model: (1) capturing and understanding the information within, among, and between generated conditional texts, (2) developing multimodal models that better integrate contextual information, and (3) designing CNLG evaluation methodologies that better align with human judgment. Through these objectives, we demonstrate the power of context in natural language generation and help to answer the question: "How can we understand, build, and evaluate context-aware models for conditional natural language generation?".
- 일반주제명
- Speech therapy
- 일반주제명
- Computer science
- 기타저자
- University of California, Berkeley Electrical Engineering & Computer Sciences
- 기본자료저록
- Dissertations Abstracts International. 86-03B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017161024
■00520250211151151
■006m o d
■007cr#unu||||||||
■020 ▼a9798384447702
■035 ▼a(MiAaPQ)AAI31235505
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a616.8
■1001 ▼aChan, David M.
■24510▼aUnderstanding, Building, and Evaluating Models for Context Aware Conditional Natural Language Generation
■260 ▼a[Sl]▼bUniversity of California, Berkeley▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a252 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-03, Section: B.
■500 ▼aAdvisor: Canny, John.
■5021 ▼aThesis (Ph.D.)--University of California, Berkeley, 2024.
■520 ▼aIf you ask a human to describe an image, they might do so in a thousand different ways. Each of these descriptions depends not only on the image but also on a rich tapestry of contextual hints and clues surrounding the image (up to and including the person doing the describing themselves). Until now, the field of conditional natural language generation has focused almost solely on the perception component of the task: how do we perceive what is in the stimulus -- be it audio, visual, or textual -- and relay it to the user? In this dissertation, we argue that models that focus solely on the stimulus (and not the associated context) suffer significant shortcomings in their ability to generate language that aligns well with human judgments of quality and content while decreasing their overall utility for downstream tasks. This dissertation focuses on three core objectives in the pursuit of building a context-aware conditional natural language generation (CNLG) model: (1) capturing and understanding the information within, among, and between generated conditional texts, (2) developing multimodal models that better integrate contextual information, and (3) designing CNLG evaluation methodologies that better align with human judgment. Through these objectives, we demonstrate the power of context in natural language generation and help to answer the question: "How can we understand, build, and evaluate context-aware models for conditional natural language generation?".
■590 ▼aSchool code: 0028.
■650 4▼aSpeech therapy
■650 4▼aComputer science
■653 ▼aAutomatic speech recognition
■653 ▼aContext-aware generation
■653 ▼aLarge language models
■653 ▼aNatural language processing
■690 ▼a0800
■690 ▼a0984
■690 ▼a0460
■71020▼aUniversity of California, Berkeley▼bElectrical Engineering & Computer Sciences.
■7730 ▼tDissertations Abstracts International▼g86-03B.
■790 ▼a0028
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161024▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
