서브메뉴
검색
Constrained, Causal, and Knowledge-Grounded Reasoning for Neural Language Generation- [electronic resource]
Constrained, Causal, and Knowledge-Grounded Reasoning for Neural Language Generation- [electronic resource]
상세정보
- 자료유형
- 학위논문파일 국외
- 최종처리일시
- 20240214101236
- ISBN
- 9798379912741
- DDC
- 620
- 저자명
- Qin, Lianhui.
- 서명/저자
- Constrained, Causal, and Knowledge-Grounded Reasoning for Neural Language Generation - [electronic resource]
- 발행사항
- [S.l.]: : University of Washington., 2023
- 발행사항
- Ann Arbor : : ProQuest Dissertations & Theses,, 2023
- 형태사항
- 1 online resource(162 p.)
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-01, Section: B.
- 주기사항
- Advisor: Choi, Yejin.
- 학위논문주기
- Thesis (Ph.D.)--University of Washington, 2023.
- 사용제한주기
- This item must not be sold to any third party vendors.
- 초록/해제
- 요약This thesis aims to establish a connection between reasoning and language generation. Today's language models (LMs, such as GPT-3), despite producing human-like fluent text, essentially act like "a mouth without a brain" -- They generate without grounding on the world knowledge, and lack the ability to flexibly reason about everyday situations and events, including counterfactual ("what if?") and abductive ("what might explain the observations?") reasoning. This thesis bridges the gap from three angles: (1) Differentiable reasoning with constraints: Humans can incorporate any constraints from the context on the fly and conduct reasoning in new situations without the need of specific training. I develop a unified inference framework that endows the LMs with the flexibility and efficiency, through a differentiable process to reason over the vast space of discrete language, combined with arbitrary neural and symbolic constraints; (2) Counterfactual and nonmonotonic reasoning in natural language: I establish the first formulation of counterfactual reasoning in language, and used my inference tool to enable the common monotonic LMs for the capabilities of nonmonotonic reasoning ranging from counterfactual, abductive, and temporal reasoning in complex context; (3) Integration of knowledge and logic in neural language models: I develop mechanisms of integrating rich external knowledge and structures with the neural LMs, to ground and boost the reasoning abilities.
- 일반주제명
- Engineering.
- 일반주제명
- Computer science.
- 키워드
- Text generation
- 기타저자
- University of Washington Computer Science and Engineering
- 기본자료저록
- Dissertations Abstracts International. 85-01B.
- 기본자료저록
- Dissertation Abstract International
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008240612s2023 us |||||||||||||||c||eng d■001000016933350
■00520240214101236
■006m o d
■007cr#unu||||||||
■020 ▼a9798379912741
■035 ▼a(MiAaPQ)AAI30527922
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a620
■1001 ▼aQin, Lianhui.
■24510▼aConstrained, Causal, and Knowledge-Grounded Reasoning for Neural Language Generation▼h[electronic resource]
■260 ▼a[S.l.]:▼bUniversity of Washington. ▼c2023
■260 1▼aAnn Arbor :▼bProQuest Dissertations & Theses, ▼c2023
■300 ▼a1 online resource(162 p.)
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-01, Section: B.
■500 ▼aAdvisor: Choi, Yejin.
■5021 ▼aThesis (Ph.D.)--University of Washington, 2023.
■506 ▼aThis item must not be sold to any third party vendors.
■520 ▼aThis thesis aims to establish a connection between reasoning and language generation. Today's language models (LMs, such as GPT-3), despite producing human-like fluent text, essentially act like "a mouth without a brain" -- They generate without grounding on the world knowledge, and lack the ability to flexibly reason about everyday situations and events, including counterfactual ("what if?") and abductive ("what might explain the observations?") reasoning. This thesis bridges the gap from three angles: (1) Differentiable reasoning with constraints: Humans can incorporate any constraints from the context on the fly and conduct reasoning in new situations without the need of specific training. I develop a unified inference framework that endows the LMs with the flexibility and efficiency, through a differentiable process to reason over the vast space of discrete language, combined with arbitrary neural and symbolic constraints; (2) Counterfactual and nonmonotonic reasoning in natural language: I establish the first formulation of counterfactual reasoning in language, and used my inference tool to enable the common monotonic LMs for the capabilities of nonmonotonic reasoning ranging from counterfactual, abductive, and temporal reasoning in complex context; (3) Integration of knowledge and logic in neural language models: I develop mechanisms of integrating rich external knowledge and structures with the neural LMs, to ground and boost the reasoning abilities.
■590 ▼aSchool code: 0250.
■650 4▼aEngineering.
■650 4▼aComputer science.
■653 ▼aCounterfactual reasoning
■653 ▼aEnergy-based modeling
■653 ▼aKnowledge grounding
■653 ▼aMachine reasoning
■653 ▼aNatural language processing
■653 ▼aText generation
■690 ▼a0800
■690 ▼a0984
■690 ▼a0537
■71020▼aUniversity of Washington▼bComputer Science and Engineering.
■7730 ▼tDissertations Abstracts International▼g85-01B.
■773 ▼tDissertation Abstract International
■790 ▼a0250
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16933350▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
■980 ▼a202402▼f2024
