본문

서브메뉴

Constructing Task-Oriented Dialogue Systems with Limited Resources
Constructing Task-Oriented Dialogue Systems with Limited Resources
Constructing Task-Oriented Dialogue Systems with Limited Resources

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152831
ISBN  
9798384296232
DDC  
004
저자명  
Qian, Kun.
서명/저자  
Constructing Task-Oriented Dialogue Systems with Limited Resources
발행사항  
[Sl] : Columbia University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
190 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-03, Section: A.
주기사항  
Advisor: Yu, Zhou.
학위논문주기  
Thesis (Ph.D.)--Columbia University, 2024.
초록/해제  
요약Task-oriented dialogue systems have increasingly become integral to our daily lives. However, collecting dialogue data is notably expensive due to the necessity of human interaction. These systems are used in various applications, such as customer service chatbots, virtual assistants, and automated scheduling tools. Given the critical role of these systems, it is essential to develop methods that can leverage limited resources efficiently, especially in data-driven models like neural networks, which have demonstrated superior performance and widespread adoption. This dissertation proposes systematic approaches to address the limited-data problem in both modeling and data aspects, aiming to enhance the effectiveness and efficiency of task-oriented dialogue systems even when data is scarce.This dissertation is divided into three main parts. The first part introduces three modeling techniques to tackle limited-data challenges. As the base dialogue model evolves from traditional recurrent neural networks to advanced large language models, we explore meta-learning methods, meta-in-context learning, and pre-training sequentially. Besides modeling considerations, the second part of our discussion emphasizes evaluation benchmarks. We start by discussing our work on correcting MultiWOZ, one of the most popular task-oriented dialogue datasets, which enhances training and provides more accurate evaluations. We also investigate biases within this dataset and propose methods to mitigate them. Additionally, we aim to improve the dataset by extending it to a multilingual dataset, facilitating the development of task-oriented dialogue systems for a global audience. The last part examines how to adapt our methods to real-world applications. We address the issue of database-search-result ambiguity in Meta's virtual assistants by constructing disambiguation dialogue turns in the training data. Furthermore, we aim to enhance Walmart's shopping companion by synthesizing high-quality knowledge-based question-answer pairs and constructing dialogue data from the bottom up.Throughout this dissertation, the consistent focus is on developing effective approaches to building task-oriented dialogue systems with limited resources. Our strategies include leveraging limited data more efficiently, utilizing data from other domains, improving data quality, and distilling knowledge from pre-trained models. We hope our approach will contribute to the field of dialogue systems and natural language processing, particularly in building applications involving real-world limited data and minimizing the need for manual data construction efforts. By addressing these challenges, this dissertation aims to lay the groundwork for creating more robust, efficient, and scalable task-oriented dialogue systems that better serve diverse user needs across various industrial applications.
일반주제명  
Computer science
일반주제명  
Information science
키워드  
Few-shot learning
키워드  
Large language model
키워드  
Meta learning
키워드  
Natural language processing
키워드  
Task-oriented dialogue
기타저자  
Columbia University Computer Science
기본자료저록  
Dissertations Abstracts International. 86-03A.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017164094
■00520250211152831
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384296232
■035    ▼a(MiAaPQ)AAI31560535
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aQian,  Kun.
■24510▼aConstructing  Task-Oriented  Dialogue  Systems  with  Limited  Resources
■260    ▼a[Sl]▼bColumbia  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a190  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-03,  Section:  A.
■500    ▼aAdvisor:  Yu,  Zhou.
■5021  ▼aThesis  (Ph.D.)--Columbia  University,  2024.
■520    ▼aTask-oriented  dialogue  systems  have  increasingly  become  integral  to  our  daily  lives.  However,  collecting  dialogue  data  is  notably  expensive  due  to  the  necessity  of  human  interaction.  These  systems  are  used  in  various  applications,  such  as  customer  service  chatbots,  virtual  assistants,  and  automated  scheduling  tools.  Given  the  critical  role  of  these  systems,  it  is  essential  to  develop  methods  that  can  leverage  limited  resources  efficiently,  especially  in  data-driven  models  like  neural  networks,  which  have  demonstrated  superior  performance  and  widespread  adoption.  This  dissertation  proposes  systematic  approaches  to  address  the  limited-data  problem  in  both  modeling  and  data  aspects,  aiming  to  enhance  the  effectiveness  and  efficiency  of  task-oriented  dialogue  systems  even  when  data  is  scarce.This  dissertation  is  divided  into  three  main  parts.  The  first  part  introduces  three  modeling  techniques  to  tackle  limited-data  challenges.  As  the  base  dialogue  model  evolves  from  traditional  recurrent  neural  networks  to  advanced  large  language  models,  we  explore  meta-learning  methods,  meta-in-context  learning,  and  pre-training  sequentially.  Besides  modeling  considerations,  the  second  part  of  our  discussion  emphasizes  evaluation  benchmarks.  We  start  by  discussing  our  work  on  correcting  MultiWOZ,  one  of  the  most  popular  task-oriented  dialogue  datasets,  which  enhances  training  and  provides  more  accurate  evaluations.  We  also  investigate  biases  within  this  dataset  and  propose  methods  to  mitigate  them.  Additionally,  we  aim  to  improve  the  dataset  by  extending  it  to  a  multilingual  dataset,  facilitating  the  development  of  task-oriented  dialogue  systems  for  a  global  audience.  The  last  part  examines  how  to  adapt  our  methods  to  real-world  applications.  We  address  the  issue  of  database-search-result  ambiguity  in  Meta's  virtual  assistants  by  constructing  disambiguation  dialogue  turns  in  the  training  data.  Furthermore,  we  aim  to  enhance  Walmart's  shopping  companion  by  synthesizing  high-quality  knowledge-based  question-answer  pairs  and  constructing  dialogue  data  from  the  bottom  up.Throughout  this  dissertation,  the  consistent  focus  is  on  developing  effective  approaches  to  building  task-oriented  dialogue  systems  with  limited  resources.  Our  strategies  include  leveraging  limited  data  more  efficiently,  utilizing  data  from  other  domains,  improving  data  quality,  and  distilling  knowledge  from  pre-trained  models.  We  hope  our  approach  will  contribute  to  the  field  of  dialogue  systems  and  natural  language  processing,  particularly  in  building  applications  involving  real-world  limited  data  and  minimizing  the  need  for  manual  data  construction  efforts.  By  addressing  these  challenges,  this  dissertation  aims  to  lay  the  groundwork  for  creating  more  robust,  efficient,  and  scalable  task-oriented  dialogue  systems  that  better  serve  diverse  user  needs  across  various  industrial  applications.
■590    ▼aSchool  code:  0054.
■650  4▼aComputer  science
■650  4▼aInformation  science
■653    ▼aFew-shot  learning
■653    ▼aLarge  language  model
■653    ▼aMeta  learning
■653    ▼aNatural  language  processing
■653    ▼aTask-oriented  dialogue
■690    ▼a0984
■690    ▼a0800
■690    ▼a0723
■71020▼aColumbia  University▼bComputer  Science.
■7730  ▼tDissertations  Abstracts  International▼g86-03A.
■790    ▼a0054
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164094▼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
    TF10697 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.