본문

서브메뉴

Incidental Supervision for Natural Language Understanding- [electronic resource]
Incidental Supervision for Natural Language Understanding - [electronic resource]
Incidental Supervision for Natural Language Understanding- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214100123
ISBN  
9798379751050
DDC  
004
저자명  
He, Hangfeng.
서명/저자  
Incidental Supervision for Natural Language Understanding - [electronic resource]
발행사항  
[S.l.]: : University of Pennsylvania., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(175 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 84-12, Section: A.
주기사항  
Advisor: Roth, Dan.
학위논문주기  
Thesis (Ph.D.)--University of Pennsylvania, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약Acquiring human annotations for natural language understanding (NLU) tasks is often labor-intensive and demands significant domain-specific expertise, making it crucial to obtain supervision from indirect signals to improve target task performance. This dissertation presents a novel approach for enhancing NLU by harnessing on the power of incidental supervision signals, which are present in the data and the environment, regardless of the specific tasks being considered.The primary aim of this research is to deepen our understanding of incidental supervision signals and to develop efficient algorithms for their acquisition, selection, and usage in NLU tasks. This problem presents numerous challenges, including the intricate nature of natural language and the inherent disparities between incidental supervision signals and target tasks. To tackle these challenges, this dissertation employs a multifaceted approach. First, we demonstrate the feasibility of utilizing cost-effective signals to enhance various target tasks. Specifically, we retrieve signals from sentence-level question-answer pairs to help NLU tasks via two types of sentence encoding approaches, depending on whether the target task involves single- or multi-sentence input.Second, we introduce a unified informativeness measure to quantitatively assess the effectiveness of diverse incidental supervision signals for a given target task. This approach offers a promising way to determine, ahead of learning, which supervision signals would be beneficial.Finally, we present a suite of efficient algorithms for exploiting distinct types of incidental supervision signals, including a weighting strategy to enhance sample efficiency in cross-task learning and a post-processing technique for faithful large language model inference with external knowledge.
일반주제명  
Computer science.
일반주제명  
Information technology.
일반주제명  
Information science.
키워드  
Natural language understanding
키워드  
Supervision signals
키워드  
Human annotations
키워드  
Challenges
키워드  
Learning
키워드  
Target task
기타저자  
University of Pennsylvania Computer and Information Science
기본자료저록  
Dissertations Abstracts International. 84-12A.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016931821
■00520240214100123
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798379751050
■035    ▼a(MiAaPQ)AAI30424791
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aHe,  Hangfeng.
■24510▼aIncidental  Supervision  for  Natural  Language  Understanding▼h[electronic  resource]
■260    ▼a[S.l.]:▼bUniversity  of  Pennsylvania.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(175  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  84-12,  Section:  A.
■500    ▼aAdvisor:  Roth,  Dan.
■5021  ▼aThesis  (Ph.D.)--University  of  Pennsylvania,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aAcquiring  human  annotations  for  natural  language  understanding  (NLU)  tasks  is  often  labor-intensive  and  demands  significant  domain-specific  expertise,  making  it  crucial  to  obtain  supervision  from  indirect  signals  to  improve  target  task  performance.  This  dissertation  presents  a  novel  approach  for  enhancing  NLU  by  harnessing  on  the  power  of  incidental  supervision  signals,  which  are  present  in  the  data  and  the  environment,  regardless  of  the  specific  tasks  being  considered.The  primary  aim  of  this  research  is  to  deepen  our  understanding  of  incidental  supervision  signals  and  to  develop  efficient  algorithms  for  their  acquisition,  selection,  and  usage  in  NLU  tasks.  This  problem  presents  numerous  challenges,  including  the  intricate  nature  of  natural  language  and  the  inherent  disparities  between  incidental  supervision  signals  and  target  tasks.  To  tackle  these  challenges,  this  dissertation  employs  a  multifaceted  approach.  First,  we  demonstrate  the  feasibility  of  utilizing  cost-effective  signals  to  enhance  various  target  tasks.  Specifically,  we  retrieve  signals  from  sentence-level  question-answer  pairs  to  help  NLU  tasks  via  two  types  of  sentence  encoding  approaches,  depending  on  whether  the  target  task  involves  single-  or  multi-sentence  input.Second,  we  introduce  a  unified  informativeness  measure  to  quantitatively  assess  the  effectiveness  of  diverse  incidental  supervision  signals  for  a  given  target  task.  This  approach  offers  a  promising  way  to  determine,  ahead  of  learning,  which  supervision  signals  would  be  beneficial.Finally,  we  present  a  suite  of  efficient  algorithms  for  exploiting  distinct  types  of  incidental  supervision  signals,  including  a  weighting  strategy  to  enhance  sample  efficiency  in  cross-task  learning  and  a  post-processing  technique  for  faithful  large  language  model  inference  with  external  knowledge.
■590    ▼aSchool  code:  0175.
■650  4▼aComputer  science.
■650  4▼aInformation  technology.
■650  4▼aInformation  science.
■653    ▼aNatural  language  understanding
■653    ▼aSupervision  signals
■653    ▼aHuman  annotations
■653    ▼aChallenges
■653    ▼aLearning
■653    ▼aTarget  task
■690    ▼a0984
■690    ▼a0489
■690    ▼a0723
■71020▼aUniversity  of  Pennsylvania▼bComputer  and  Information  Science.
■7730  ▼tDissertations  Abstracts  International▼g84-12A.
■773    ▼tDissertation  Abstract  International
■790    ▼a0175
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16931821▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF06609 전자도서 마이폴더 부재도서신고 비도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.