본문

서브메뉴

Understanding and Reasoning About Implicit Meaning in Language
Understanding and Reasoning About Implicit Meaning in Language
Understanding and Reasoning About Implicit Meaning in Language

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211151155
ISBN  
9798382310503
DDC  
004
저자명  
Allaway, Emily.
서명/저자  
Understanding and Reasoning About Implicit Meaning in Language
발행사항  
[Sl] : Columbia University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
317 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-10, Section: A.
주기사항  
Advisor: McKeown, Kathleen.
학위논문주기  
Thesis (Ph.D.)--Columbia University, 2024.
초록/해제  
요약Enabling machines to interact with humans requires understanding what people mean, even when they do not say it explicitly. For example, machines should understand that "selfish people oppose gun control'' implies a pro-gun control viewpoint (i.e., is taking a stance in support of gun control) despite the negative tone of the statement. Understanding these types of pragmatic inferences allows humans to grasp meaning (e.g., intentions, relevant facts) beyond what is literally expressed in an utterance. Furthermore, pragmatic inferences conveyed through generalizations (e.g., referring to generic "selfish people'' rather than specific individuals in order to be more persuasive) support flexible and efficient reasoning. Therefore, in this thesis we focus on improving computational understanding of two inter-related types of pragmatic inferences: stance taking and linguistic generalizations.This thesis is divided into two parts. In Part II, we focus on stance detection. One major challenge for stance detection models is the large and continually growing set of stance targets (i.e., topics to take a stance on). Therefore, to address this we define and study zero-shot stance detection (i.e., evaluation on topics for which there is no training data). Our work develops both datasets and models for this task and analyzes the ongoing challenges for future work. This work has stimulated increasing and ongoing research in zero-shot stance detection in NLP.Then in Part I we study generics --- a specific type of linguistic generalization that does not contain explicit quantifiers (e.g., "most'', "some''). These statements can have strong persuasive force and are also related to complex patterns of reasoning. To probe the current understanding capabilities of computational models, we focus on generating generics exemplars --- specific cases when a generic holds true or false. In particular, we propose computational frameworks grounded in linguistic theory to generate the first datasets of exemplars. We then use our datasets to highlight the challenges generics pose for natural language reasoning and the current generic-understanding capabilities of large language models.
일반주제명  
Computer science
일반주제명  
Linguistics
일반주제명  
Philosophy
일반주제명  
Information science
키워드  
Generics
키워드  
Natural language processing
키워드  
Stances
키워드  
Linguistic generalizations
키워드  
Implicit meaning
기타저자  
Columbia University Computer Science
기본자료저록  
Dissertations Abstracts International. 85-10A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017161049
■00520250211151155
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382310503
■035    ▼a(MiAaPQ)AAI31236225
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aAllaway,  Emily.
■24510▼aUnderstanding  and  Reasoning  About  Implicit  Meaning  in  Language
■260    ▼a[Sl]▼bColumbia  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a317  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-10,  Section:  A.
■500    ▼aAdvisor:  McKeown,  Kathleen.
■5021  ▼aThesis  (Ph.D.)--Columbia  University,  2024.
■520    ▼aEnabling  machines  to  interact  with  humans  requires  understanding  what  people  mean,  even  when  they  do  not  say  it  explicitly.  For  example,  machines  should  understand  that  "selfish  people  oppose  gun  control''  implies  a  pro-gun  control  viewpoint  (i.e.,  is  taking  a  stance  in  support  of  gun  control)  despite  the  negative  tone  of  the  statement.  Understanding  these  types  of  pragmatic  inferences  allows  humans  to  grasp  meaning  (e.g.,  intentions,  relevant  facts)  beyond  what  is  literally  expressed  in  an  utterance.  Furthermore,  pragmatic  inferences  conveyed  through  generalizations  (e.g.,  referring  to  generic  "selfish  people''  rather  than  specific  individuals  in  order  to  be  more  persuasive)  support  flexible  and  efficient  reasoning.  Therefore,  in  this  thesis  we  focus  on  improving  computational  understanding  of  two  inter-related  types  of  pragmatic  inferences:  stance  taking  and  linguistic  generalizations.This  thesis  is  divided  into  two  parts.  In  Part  II,  we  focus  on  stance  detection.  One  major  challenge  for  stance  detection  models  is  the  large  and  continually  growing  set  of  stance  targets  (i.e.,  topics  to  take  a  stance  on).  Therefore,  to  address  this  we  define  and  study  zero-shot  stance  detection  (i.e.,  evaluation  on  topics  for  which  there  is  no  training  data).  Our  work  develops  both  datasets  and  models  for  this  task  and  analyzes  the  ongoing  challenges  for  future  work.  This  work  has  stimulated  increasing  and  ongoing  research  in  zero-shot  stance  detection  in  NLP.Then  in  Part  I  we  study  generics  ---  a  specific  type  of  linguistic  generalization  that  does  not  contain  explicit  quantifiers  (e.g.,  "most'',  "some'').  These  statements  can  have  strong  persuasive  force  and  are  also  related  to  complex  patterns  of  reasoning.  To  probe  the  current  understanding  capabilities  of  computational  models,  we  focus  on  generating  generics  exemplars  ---  specific  cases  when  a  generic  holds  true  or  false.  In  particular,  we  propose  computational  frameworks  grounded  in  linguistic  theory  to  generate  the  first  datasets  of  exemplars.  We  then  use  our  datasets  to  highlight  the  challenges  generics  pose  for  natural  language  reasoning  and  the  current  generic-understanding  capabilities  of  large  language  models.
■590    ▼aSchool  code:  0054.
■650  4▼aComputer  science
■650  4▼aLinguistics
■650  4▼aPhilosophy
■650  4▼aInformation  science
■653    ▼aGenerics
■653    ▼aNatural  language  processing
■653    ▼aStances
■653    ▼aLinguistic  generalizations
■653    ▼aImplicit  meaning
■690    ▼a0984
■690    ▼a0422
■690    ▼a0723
■690    ▼a0290
■71020▼aColumbia  University▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g85-10A.
■790    ▼a0054
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161049▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

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
    TF11765 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

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

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.