본문

서브메뉴

Generating Semantic Graphs for Natural Language- [electronic resource]
Generating Semantic Graphs for Natural Language - [electronic resource]
Generating Semantic Graphs for Natural Language- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214100457
ISBN  
9798379604158
DDC  
004
저자명  
Zhou, Jiawei.
서명/저자  
Generating Semantic Graphs for Natural Language - [electronic resource]
발행사항  
[S.l.]: : Harvard University., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(189 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
주기사항  
Advisor: Rush, Alexander M. ;Yu, Minlan.
학위논문주기  
Thesis (Ph.D.)--Harvard University, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약Natural language understanding is a critical capability in achieving advanced artificial intelligent language processing systems such as reading comprehension, question answering, and interactive dialogues. Despite the remarkable progress made by modern deep learning techniques for natural language processing (NLP) in the past decade, machines still lag behind human capacity in deep language understanding. This requires machines to represent and comprehend the underlying meaning, or semantics, from the surface form of language despite its variations and intricacies. Explicit semantic representations of language provide a systematic way of building interpretable and controllable agents with language understanding ability, especially with versatile graph structures. Abstracting away from the surface form of language, the semantic graphs can capture complex semantic phenomena, and provide a structured and consistent way of presenting the underlying meaning of language, which can be utilized for applications that require accurate semantic interpretation. Depending on applications, certain semantic graphs such as functional programs can also be executable for direct machine processing, paving ways for interactive and efficient human-machine communication. However, the complexity of the structured graphs and the expensiveness of expert data annotation pose unique challenges in automating the generation process of these graphs.In this thesis, we develop techniques using machine learning models to generate such semantic graphs for natural language, as well as exploring efficient utilization of these graphs in real applications such as dialogue systems. We first formulate a general framework for text-to-graph generation with an autoregressive process through a carefully designed sequence of actions, and then devise a principled approach that combines the general graph construction process and neural models such as sequence-to-sequence Transformer models and pointer networks with synergy. We apply the proposed method to interpret natural language sentences into abstract semantic graphs, where the end-to-end deep learning model is guided by carefully designed logic-based state machines that manage the graph and action transduction. The hybrid approach injects an effective form of structured inductive bias in the model computation, resulting in high-quality graph generation without complex modeling pipelines. With recent advances of pre-trained language models benefiting from large amounts of unlabeled data, we further study the effective way of merging the benefits of these unstructured models with structured generation of semantic graphs to increase data efficiency. Furthermore, we extend our text-to-graph generation framework for executable semantic graphs that are programs serving as essential building blocks of a reliable task-oriented dialogue system. We propose a novel online semantic parsing paradigm which aims to generate and execute partial semantic graphs simultaneously as the sentence is being revealed. The application enables real-time interpretation of human utterances to accelerate machine response, making human-machine interaction experience more natural. We hope our research on text-to-graph generation and application not only sheds some light on natural language understanding and reliable semantic-aware system building, but also creates further opportunities for interdisciplinary research beyond NLP where symbolic graph-structured data modeling and generation are of vital importance.
일반주제명  
Computer science.
일반주제명  
Linguistics.
일반주제명  
Information science.
키워드  
Dialogue system
키워드  
Graph generation
키워드  
Natural language processing understanding
키워드  
Online semantic parsing
키워드  
Semantic graphs
키워드  
Structured prediction
기타저자  
Harvard University Engineering and Applied Sciences - Engineering Sciences
기본자료저록  
Dissertations Abstracts International. 84-12B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016932430
■00520240214100457
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798379604158
■035    ▼a(MiAaPQ)AAI30492497
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aZhou,  Jiawei.▼0(orcid)0000-0001-5590-6270
■24510▼aGenerating  Semantic  Graphs  for  Natural  Language▼h[electronic  resource]
■260    ▼a[S.l.]:▼bHarvard  University.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(189  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  84-12,  Section:  B.
■500    ▼aAdvisor:  Rush,  Alexander  M.  ;Yu,  Minlan.
■5021  ▼aThesis  (Ph.D.)--Harvard  University,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aNatural  language  understanding  is  a  critical  capability  in  achieving  advanced  artificial  intelligent  language  processing  systems  such  as  reading  comprehension,  question  answering,  and  interactive  dialogues.  Despite  the  remarkable  progress  made  by  modern  deep  learning  techniques  for  natural  language  processing  (NLP)  in  the  past  decade,  machines  still  lag  behind  human  capacity  in  deep  language  understanding.  This  requires  machines  to  represent  and  comprehend  the  underlying  meaning,  or  semantics,  from  the  surface  form  of  language  despite  its  variations  and  intricacies.  Explicit  semantic  representations  of  language  provide  a  systematic  way  of  building  interpretable  and  controllable  agents  with  language  understanding  ability,  especially  with  versatile  graph  structures.  Abstracting  away  from  the  surface  form  of  language,  the  semantic  graphs  can  capture  complex  semantic  phenomena,  and  provide  a  structured  and  consistent  way  of  presenting  the  underlying  meaning  of  language,  which  can  be  utilized  for  applications  that  require  accurate  semantic  interpretation.  Depending  on  applications,  certain  semantic  graphs  such  as  functional  programs  can  also  be  executable  for  direct  machine  processing,  paving  ways  for  interactive  and  efficient  human-machine  communication.  However,  the  complexity  of  the  structured  graphs  and  the  expensiveness  of  expert  data  annotation  pose  unique  challenges  in  automating  the  generation  process  of  these  graphs.In  this  thesis,  we  develop  techniques  using  machine  learning  models  to  generate  such  semantic  graphs  for  natural  language,  as  well  as  exploring  efficient  utilization  of  these  graphs  in  real  applications  such  as  dialogue  systems.  We  first  formulate  a  general  framework  for  text-to-graph  generation  with  an  autoregressive  process  through  a  carefully  designed  sequence  of  actions,  and  then  devise  a  principled  approach  that  combines  the  general  graph  construction  process  and  neural  models  such  as  sequence-to-sequence  Transformer  models  and  pointer  networks  with  synergy.  We  apply  the  proposed  method  to  interpret  natural  language  sentences  into  abstract  semantic  graphs,  where  the  end-to-end  deep  learning  model  is  guided  by  carefully  designed  logic-based  state  machines  that  manage  the  graph  and  action  transduction.  The  hybrid  approach  injects  an  effective  form  of  structured  inductive  bias  in  the  model  computation,  resulting  in  high-quality  graph  generation  without  complex  modeling  pipelines.  With  recent  advances  of  pre-trained  language  models  benefiting  from  large  amounts  of  unlabeled  data,  we  further  study  the  effective  way  of  merging  the  benefits  of  these  unstructured  models  with  structured  generation  of  semantic  graphs  to  increase  data  efficiency. Furthermore,  we  extend  our  text-to-graph  generation  framework  for  executable  semantic  graphs  that  are  programs  serving  as  essential  building  blocks  of  a  reliable  task-oriented  dialogue  system.  We  propose  a  novel  online  semantic  parsing  paradigm  which  aims  to  generate  and  execute  partial  semantic  graphs  simultaneously  as  the  sentence  is  being  revealed.  The  application  enables  real-time  interpretation  of  human  utterances  to  accelerate  machine  response,  making  human-machine  interaction  experience  more  natural.  We  hope  our  research  on  text-to-graph  generation  and  application  not  only  sheds  some  light  on  natural  language  understanding  and  reliable  semantic-aware  system  building,  but  also  creates  further  opportunities  for  interdisciplinary  research  beyond  NLP  where  symbolic  graph-structured  data  modeling  and  generation  are  of  vital  importance.
■590    ▼aSchool  code:  0084.
■650  4▼aComputer  science.
■650  4▼aLinguistics.
■650  4▼aInformation  science.
■653    ▼aDialogue  system
■653    ▼aGraph  generation
■653    ▼aNatural  language  processing  understanding
■653    ▼aOnline  semantic  parsing
■653    ▼aSemantic  graphs
■653    ▼aStructured  prediction
■690    ▼a0984
■690    ▼a0290
■690    ▼a0723
■71020▼aHarvard  University▼bEngineering  and  Applied  Sciences  -  Engineering  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g84-12B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0084
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16932430▼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
    TF06699 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.