서브메뉴
검색
Leveraging Textual Semantics for Knowledge Graph Acquisition and Application- [electronic resource]
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
- Knowledge Graphs
- 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


