본문

서브메뉴

Leveraging Textual Semantics for Knowledge Graph Acquisition and Application- [electronic resource]
Leveraging Textual Semantics for Knowledge Graph Acquisition and Application - [electronic...
Leveraging Textual Semantics for Knowledge Graph Acquisition and Application- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214101911
ISBN  
9798380855587
DDC  
621.3
저자명  
Yu, Donghan.
서명/저자  
Leveraging Textual Semantics for Knowledge Graph Acquisition and Application - [electronic resource]
발행사항  
[S.l.]: : Carnegie Mellon University., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(106 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 85-05, Section: B.
주기사항  
Advisor: Yang, Yiming.
학위논문주기  
Thesis (Ph.D.)--Carnegie Mellon University, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약Knowledge Graphs (KGs), which represent world knowledge through entities and relations, are ubiquitous in real-world applications. Besides their structural nature, KGs offer rich textual information, as entities usually correspond to real-world objects with specific names and descriptions. Despite the importance of such information, it has been largely overlooked or inadequately explored in existing studies.This thesis aims to integrate the textual information into the modeling of KGs by utilizing Pre-trained Language Models (PLMs), which have demonstrated effectiveness in capturing the semantic meanings of natural language. This goal is carried out on two complementary parts: the acquisition of KGs to enhance their qualities, and the application of KGs to address user queries.In Part I, we focus on KG acquisition through text. We begin with a pre-training framework that jointly learns the vector representations of KGs and text. It features KG-text dual modules that mutually enhance each other, achieving strong results on relation extraction and entity classification. (Chapter 2). To address scalability challenges in large KGs, we propose a retrieval-enhanced text-generation model for KG completion. It leverages semantically relevant triplets from KGs to guide the generation of missing entities, demonstrating state-of-the-art performance while maintaining low memory usage (Chapter 3).In Part II, we turn our attention to applying KGs to the crucial task of Question Answering (QA). In the setting that the answers are sourced from KGs, we propose a framework that jointly generates logical queries and text answers to produce more accurate and robust results (Chapter 4). Then we extend to the scenarios where the answers mainly stem from text corpora instead of KGs. Our proposed method leverages KGs to construct links among the text passages. Such structural information is leveraged to re-rank and prune related passages for each question, significantly reducing computational costs (Chapter 5). Finally, we tackle the setting of incomplete KGs. We introduce the first benchmark dataset to assess the impact of KG completion methods on question answering. Our experiments highlight the necessity to jointly study the acquisition and application of KGs (Chapter 6).
일반주제명  
Computer engineering.
일반주제명  
Computer science.
키워드  
Graph neural network
키워드  
Knowledge Graphs
키워드  
Pre-trained language model
키워드  
Question answering
키워드  
Textual semantics
기타저자  
Carnegie Mellon University Language Technologies Institute
기본자료저록  
Dissertations Abstracts International. 85-05B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016935259
■00520240214101911
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380855587
■035    ▼a(MiAaPQ)AAI30686840
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aYu,  Donghan.
■24510▼aLeveraging  Textual  Semantics  for  Knowledge  Graph  Acquisition  and  Application▼h[electronic  resource]
■260    ▼a[S.l.]:▼bCarnegie  Mellon  University.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(106  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-05,  Section:  B.
■500    ▼aAdvisor:  Yang,  Yiming.
■5021  ▼aThesis  (Ph.D.)--Carnegie  Mellon  University,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aKnowledge  Graphs  (KGs),  which  represent  world  knowledge  through  entities  and  relations,  are  ubiquitous  in  real-world  applications.  Besides  their  structural  nature,  KGs  offer  rich  textual  information,  as  entities  usually  correspond  to  real-world  objects  with  specific  names  and  descriptions.  Despite  the  importance  of  such  information,  it  has  been  largely  overlooked  or  inadequately  explored  in  existing  studies.This  thesis  aims  to  integrate  the  textual  information  into  the  modeling  of  KGs  by  utilizing  Pre-trained  Language  Models  (PLMs),  which  have  demonstrated  effectiveness  in  capturing  the  semantic  meanings  of  natural  language.  This  goal  is  carried  out  on  two  complementary  parts:  the  acquisition  of  KGs  to  enhance  their  qualities,  and  the  application  of  KGs  to  address  user  queries.In  Part  I,  we  focus  on  KG  acquisition  through  text.  We  begin  with  a  pre-training  framework  that  jointly  learns  the  vector  representations  of  KGs  and  text.  It  features  KG-text  dual  modules  that  mutually  enhance  each  other,  achieving  strong  results  on  relation  extraction  and  entity  classification.  (Chapter  2).  To  address  scalability  challenges  in  large  KGs,  we  propose  a  retrieval-enhanced  text-generation  model  for  KG  completion.  It  leverages  semantically  relevant  triplets  from  KGs  to  guide  the  generation  of  missing  entities,  demonstrating  state-of-the-art  performance  while  maintaining  low  memory  usage  (Chapter  3).In  Part  II,  we  turn  our  attention  to  applying  KGs  to  the  crucial  task  of  Question  Answering  (QA).  In  the  setting  that  the  answers  are  sourced  from  KGs,  we  propose  a  framework  that  jointly  generates  logical  queries  and  text  answers  to  produce  more  accurate  and  robust  results  (Chapter  4).  Then  we  extend  to  the  scenarios  where  the  answers  mainly  stem  from  text  corpora  instead  of  KGs.  Our  proposed  method  leverages  KGs  to  construct  links  among  the  text  passages.  Such  structural  information  is  leveraged  to  re-rank  and  prune  related  passages  for  each  question,  significantly  reducing  computational  costs  (Chapter  5).  Finally,  we  tackle  the  setting  of  incomplete  KGs.  We  introduce  the  first  benchmark  dataset  to  assess  the  impact  of  KG  completion  methods  on  question  answering.  Our  experiments  highlight  the  necessity  to  jointly  study  the  acquisition  and  application  of  KGs  (Chapter  6).
■590    ▼aSchool  code:  0041.
■650  4▼aComputer  engineering.
■650  4▼aComputer  science.
■653    ▼aGraph  neural  network
■653    ▼aKnowledge  Graphs
■653    ▼aPre-trained  language  model
■653    ▼aQuestion  answering
■653    ▼aTextual  semantics
■690    ▼a0800
■690    ▼a0984
■690    ▼a0464
■71020▼aCarnegie  Mellon  University▼bLanguage  Technologies  Institute.
■7730  ▼tDissertations  Abstracts  International▼g85-05B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0041
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16935259▼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
    TF05799 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.