본문

서브메뉴

Grounded and Consistent Question Answering- [electronic resource]
Grounded and Consistent Question Answering- [electronic resource]

상세정보

자료유형  
 학위논문
Control Number  
0016935039
International Standard Book Number  
9798380340373
Dewey Decimal Classification Number  
004
Main Entry-Personal Name  
Alberti, Christopher.
Publication, Distribution, etc. (Imprint  
[S.l.] : Columbia University., 2023
Publication, Distribution, etc. (Imprint  
Ann Arbor : ProQuest Dissertations & Theses, 2023
Physical Description  
1 online resource(173 p.)
General Note  
Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
General Note  
Advisor: Hirschberg, Julia;Collins, Michael.
Dissertation Note  
Thesis (Ph.D.)--Columbia University, 2023.
Restrictions on Access Note  
This item must not be sold to any third party vendors.
Summary, Etc.  
요약This thesis describes advancements in question answering along three general directions: model architecture extensions, explainable question answering, and data augmentation. Chapter 2 describes the first state-of-the-art model for the Natural Questions dataset based on pretrained transformers. Chapters 3 and 4 describe extensions to the model architecture designed to accomodate long textual inputs and multimodal text+image inputs, establishing new state-of-the-art results on the Natural Questions and on the VCR dataset. Chapter 5 shows that significant improvements can be obtained with data augmentation on the SQuAD and Natural Questions dataset, introducing roundtrip consistency as a simple heuristic to improve the quality of synthetic data. In Chapters 6 and 7 we explore explainable question answering, demonstrating the usefulness of a new concrete kind of structured explanations, QED, and proposing a semantic analysis of why-questions in the Natural Questions, as a way of better understanding the nature of real world explanations. Finally, in Chapters 8 and 9 we delve into more exploratory data augmentation techniques for question answering. We look respectively at how straight-through gradients can be utilized to optimize roundtrip consistency in a pipeline of models on the fly, and at how very recent large language models like PaLM can be used to generate synthetic question answering datasets for new languages given as few as five representative examples per language.
Subject Added Entry-Topical Term  
Computer science.
Subject Added Entry-Topical Term  
Computer engineering.
Index Term-Uncontrolled  
Architecture extensions
Index Term-Uncontrolled  
Data augmentation
Index Term-Uncontrolled  
Structured explanations
Index Term-Uncontrolled  
Semantic analysis
Index Term-Uncontrolled  
Synthetic data
Added Entry-Corporate Name  
Columbia University Computer Science
Host Item Entry  
Dissertations Abstracts International. 85-03B.
Host Item Entry  
Dissertation Abstract International
Electronic Location and Access  
로그인을 한후 보실 수 있는 자료입니다.
Control Number  
joongbu:640734

MARC

 008240220s2023        ulk                      00        kor
■001000016935039
■00520240214101846
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380340373
■035    ▼a(MiAaPQ)AAI30639152
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aAlberti,  Christopher.
■24510▼aGrounded  and  Consistent  Question  Answering▼h[electronic  resource]
■260    ▼a[S.l.]▼bColumbia  University.  ▼c2023
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2023
■300    ▼a1  online  resource(173  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-03,  Section:  B.
■500    ▼aAdvisor:  Hirschberg,  Julia;Collins,  Michael.
■5021  ▼aThesis  (Ph.D.)--Columbia  University,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aThis  thesis  describes  advancements  in  question  answering  along  three  general  directions:  model  architecture  extensions,  explainable  question  answering,  and  data  augmentation.  Chapter  2  describes  the  first  state-of-the-art  model  for  the  Natural  Questions  dataset  based  on  pretrained  transformers.  Chapters  3  and  4  describe  extensions  to  the  model  architecture  designed  to  accomodate  long  textual  inputs  and  multimodal  text+image  inputs,  establishing  new  state-of-the-art  results  on  the  Natural  Questions  and  on  the  VCR  dataset.  Chapter  5  shows  that  significant  improvements  can  be  obtained  with  data  augmentation  on  the  SQuAD  and  Natural  Questions  dataset,  introducing  roundtrip  consistency  as  a  simple  heuristic  to  improve  the  quality  of  synthetic  data.  In  Chapters  6  and  7  we  explore  explainable  question  answering,  demonstrating  the  usefulness  of  a  new  concrete  kind  of  structured  explanations,  QED,  and  proposing  a  semantic  analysis  of  why-questions  in  the  Natural  Questions,  as  a  way  of  better  understanding  the  nature  of  real  world  explanations.  Finally,  in  Chapters  8  and  9  we  delve  into  more  exploratory  data  augmentation  techniques  for  question  answering.  We  look  respectively  at  how  straight-through  gradients  can  be  utilized  to  optimize  roundtrip  consistency  in  a  pipeline  of  models  on  the  fly,  and  at  how  very  recent  large  language  models  like  PaLM  can  be  used  to  generate  synthetic  question  answering  datasets  for  new  languages  given  as  few  as  five  representative  examples  per  language.
■590    ▼aSchool  code:  0054.
■650  4▼aComputer  science.
■650  4▼aComputer  engineering.
■653    ▼aArchitecture  extensions
■653    ▼aData  augmentation
■653    ▼aStructured  explanations
■653    ▼aSemantic  analysis
■653    ▼aSynthetic  data
■690    ▼a0984
■690    ▼a0464
■71020▼aColumbia  University▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g85-03B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0054
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16935039▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    New Books MORE
    Related books MORE
    최근 3년간 통계입니다.

    detalle info

    • Reserva
    • 캠퍼스간 도서대출
    • 서가에 없는 책 신고
    • Mi carpeta
    Material
    número de libro número de llamada Ubicación estado Prestar info
    TQ0026658 T   원문자료 열람가능/출력가능 열람가능/출력가능
    마이폴더 부재도서신고

    * Las reservas están disponibles en el libro de préstamos. Para hacer reservaciones, haga clic en el botón de reserva

    해당 도서를 다른 이용자가 함께 대출한 도서

    Related books

    Related Popular Books

    도서위치