Knowledge graphs serve as an essential source for many tasks in data mining, artificial intelligence, and interdisciplinary challenges such as entity disambiguation, fact checking, and computational journalism. However, real-world knowledge graphs are far from perfect, so it remains a crucial task to improve the quality and completeness of these essential tools.
In this work, I present a representation learning-based approach to improve the quality of knowledge graphs through a process called Knowledge Graph Completion. This process finds missing connections among entities in the graph. I also propose a relaxed version of the knowledge graph completion task called Open-world Knowledge Graph Completion to complete and extend knowledge graphs with unobserved entities. Extensive evaluations on several data sets with different sizes shows the effectiveness of proposed methods for knowledge graph completion. Further experiments also demonstrate that these models can also solve tasks beyond Knowledge Graph Completion, such as classification, clustering, and recommendation tasks based on the representations learned from the knowledge graphs.
|School:||University of Notre Dame|
|Department:||Computer Science and Engineering|
|School Location:||United States -- Indiana|
|Source:||DAI-B 80/06(E), Dissertation Abstracts International|
|Keywords:||Heterogeneous information network, Knowledge graph, Knowledge graph completion, Network representation learning|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be