Exploring and evaluating attributes, values, and structures for entity alignment

Entity alignment (EA) aims at building a unified Knowledge Graph (KG) of rich content by linking the equivalent entities from various KGs. GNN-based EA methods present promising performance by modeling the KG structure defined by relation triples. However, attribute triples can also provide crucial...

Full description

Saved in:
Bibliographic Details
Main Authors: LIU, Zhiyuan, CAO, Yixin, PAN, Liangming, LI, Juanzi, CHUA, Tat-Seng
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2020
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/7455
https://ink.library.smu.edu.sg/context/sis_research/article/8458/viewcontent/2020.emnlp_main.515.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-8458
record_format dspace
spelling sg-smu-ink.sis_research-84582022-10-20T07:22:38Z Exploring and evaluating attributes, values, and structures for entity alignment LIU, Zhiyuan CAO, Yixin PAN, Liangming LI, Juanzi LIU, Zhiyuan CHUA, Tat-Seng Entity alignment (EA) aims at building a unified Knowledge Graph (KG) of rich content by linking the equivalent entities from various KGs. GNN-based EA methods present promising performance by modeling the KG structure defined by relation triples. However, attribute triples can also provide crucial alignment signal but have not been well explored yet. In this paper, we propose to utilize an attributed value encoder and partition the KG into subgraphs to model the various types of attribute triples efficiently. Besides, the performances of current EA methods are overestimated because of the name-bias of existing EA datasets. To make an objective evaluation, we propose a hard experimental setting where we select equivalent entity pairs with very different names as the test set. Under both the regular and hard settings, our method achieves significant improvements (5.10% on average Hits@1 in DBP15k) over 12 baselines in crosslingual and monolingual datasets. Ablation studies on different subgraphs and a case study about attribute types further demonstrate the effectiveness of our method. Source code and data can be found at https://github.com/ thunlp/explore-and-evaluate. 2020-11-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7455 info:doi/10.18653/v1/2020.emnlp-main.515 https://ink.library.smu.edu.sg/context/sis_research/article/8458/viewcontent/2020.emnlp_main.515.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Databases and Information Systems
Graphics and Human Computer Interfaces
spellingShingle Databases and Information Systems
Graphics and Human Computer Interfaces
LIU, Zhiyuan
CAO, Yixin
PAN, Liangming
LI, Juanzi
LIU, Zhiyuan
CHUA, Tat-Seng
Exploring and evaluating attributes, values, and structures for entity alignment
description Entity alignment (EA) aims at building a unified Knowledge Graph (KG) of rich content by linking the equivalent entities from various KGs. GNN-based EA methods present promising performance by modeling the KG structure defined by relation triples. However, attribute triples can also provide crucial alignment signal but have not been well explored yet. In this paper, we propose to utilize an attributed value encoder and partition the KG into subgraphs to model the various types of attribute triples efficiently. Besides, the performances of current EA methods are overestimated because of the name-bias of existing EA datasets. To make an objective evaluation, we propose a hard experimental setting where we select equivalent entity pairs with very different names as the test set. Under both the regular and hard settings, our method achieves significant improvements (5.10% on average Hits@1 in DBP15k) over 12 baselines in crosslingual and monolingual datasets. Ablation studies on different subgraphs and a case study about attribute types further demonstrate the effectiveness of our method. Source code and data can be found at https://github.com/ thunlp/explore-and-evaluate.
format text
author LIU, Zhiyuan
CAO, Yixin
PAN, Liangming
LI, Juanzi
LIU, Zhiyuan
CHUA, Tat-Seng
author_facet LIU, Zhiyuan
CAO, Yixin
PAN, Liangming
LI, Juanzi
LIU, Zhiyuan
CHUA, Tat-Seng
author_sort LIU, Zhiyuan
title Exploring and evaluating attributes, values, and structures for entity alignment
title_short Exploring and evaluating attributes, values, and structures for entity alignment
title_full Exploring and evaluating attributes, values, and structures for entity alignment
title_fullStr Exploring and evaluating attributes, values, and structures for entity alignment
title_full_unstemmed Exploring and evaluating attributes, values, and structures for entity alignment
title_sort exploring and evaluating attributes, values, and structures for entity alignment
publisher Institutional Knowledge at Singapore Management University
publishDate 2020
url https://ink.library.smu.edu.sg/sis_research/7455
https://ink.library.smu.edu.sg/context/sis_research/article/8458/viewcontent/2020.emnlp_main.515.pdf
_version_ 1770576341597421568