ZeroEA: A Zero-Training Entity Alignment Framework via Pre-Trained Language Model

Nan Huo, Reynold Cheng, Ben Kao, Wentao Ning, Nur Al Hasan, Xiaodong Li, Jinyang Li, Mohammad Matin Najafi, Tian Li, Ge Qu

Research output: Chapter in Book/Conference paperConference paperpeer-review

1 Citation (Scopus)

Abstract

Entity alignment (EA), a crucial task in knowledge graph (KG) research, aims to identify equivalent entities across different KGs to support downstream tasks like KG integration, text-to-SQL, and question-answering systems. Given rich semantic information within KGs, pre-trained language models (PLMs) have shown promise in EA tasks due to their exceptional context-aware encoding capabilities. However, the current solutions based on PLMs encounter obstacles such as the need for extensive training, expensive data annotation, and inadequate incorporation of structural information. In this study, we introduce a novel zero-training EA framework, ZeroEA, which effectively captures both semantic and structural information for PLMs. To be specific, Graph2Prompt module serves as the bridge between graph structure and plain text by converting KG topology into textual context suitable for PLM input. Additionally, in order to provide PLMs with concise and clear input text of reasonable length, we design a motif-based neighborhood filter to eliminate noisy neighbors. The comprehensive experiments and analyses on 5 benchmark datasets demonstrate the effectiveness of ZeroEA, outperforming all leading competitors and achieving state-of-the-art performance in entity alignment. Notably, our study highlights the considerable potential of EA technique in improving the performance of downstream tasks, thereby benefitting the broader research field.

Original languageEnglish
Title of host publicationproceedings
Pages1765-1774
Number of pages10
Volume17
Edition7
DOIs
Publication statusPublished - 2024
Event50th International Conference on Very Large Data Bases - Guangzhou, China
Duration: 24 Aug 202429 Aug 2024

Publication series

NameProceedings of the VLDB Endowment
PublisherVery Large Data Base Endowment Inc.
ISSN (Print)2150-8097

Conference

Conference50th International Conference on Very Large Data Bases
Abbreviated titleVLDB 2024
Country/TerritoryChina
CityGuangzhou
Period24/08/2429/08/24

Fingerprint

Dive into the research topics of 'ZeroEA: A Zero-Training Entity Alignment Framework via Pre-Trained Language Model'. Together they form a unique fingerprint.

Cite this