Back to search

University of Waterloo

Cross-Lingual Entity Matching for Knowledge Graphs

Abstract

dc:description.abstract

Multilingual knowledge graphs (KGs), such as YAGO and DBpedia, represent entities in different languages. The task of cross-lingual entity matching is to align entities in a source language with their counterparts in target languages. In this thesis, we investigate embedding-based approaches to encode entities from multilingual KGs into the same vector space, where equivalent entities are close to each other. Specifically, we apply graph convolutional networks (GCNs) to combine multi-aspect information of entities, including topological connections, relations, and attributes of entities, to learn entity embeddings. To exploit the literal descriptions of entities expressed in different languages, we propose two uses of a pre-trained multilingual BERT model to bridge cross-lingual gaps. We further propose two strategies to integrate GCN-based and BERT-based modules to boost performance. Extensive experiments on two benchmark datasets demonstrate that our method significantly outperforms existing systems. We additionally introduce a new dataset comprised of 15 low-resource languages and featured with unlinkable cases to draw closer to the real-world challenges.

Degree

thesis:*
Grantor dc:publisher
University of Waterloo
Year dc:date.issued
2020

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Yang, Hsiu-Wei
Advisor dc:contributor.advisor
  • Lin, Jimmy

Subjects

dc:subject × 6

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/10012/16547

Chain of custody

source
Harvested from
University of Waterloo
Base URL
dspacemainprd01.lib.uwaterloo.ca/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Yang, Hsiu-Wei. Cross-Lingual Entity Matching for Knowledge Graphs. University of Waterloo, 2020. http://hdl.handle.net/10012/16547