Guiding cross-lingual entity alignment via adversarial knowledge embedding

Lin, X; Yang, H; Wu, J; Zhou, C; Wang, B

Guiding cross-lingual entity alignment via adversarial knowledge embedding

Lin, X Yang, H

Wu, J Zhou, C Wang, B

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: Proceedings - IEEE International Conference on Data Mining, ICDM, 2020, 2019-November, pp. 429-438
Issue Date:: 2020

Closed Access

	Filename	Description	Size
	08970718.pdf	Published version	449.36 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lin, X
dc.contributor.author	Yang, H https://orcid.org/0000-0002-4328-335X
dc.contributor.author	Wu, J
dc.contributor.author	Zhou, C
dc.contributor.author	Wang, B
dc.date	2019-11-08
dc.date.accessioned	2021-04-14T19:46:57Z
dc.date.available	2021-04-14T19:46:57Z
dc.date.issued	2020
dc.identifier.citation	Proceedings - IEEE International Conference on Data Mining, ICDM, 2020, 2019-November, pp. 429-438
dc.identifier.isbn	9781728146034
dc.identifier.issn	1550-4786
dc.identifier.issn	2374-8486
dc.identifier.uri	http://hdl.handle.net/10453/148105
dc.description.abstract	© 2019 IEEE. Cross-lingual Entity Alignment (CEA) aims at identifying entities with their counterparts in different language knowledge graphs. Knowledge embedding alignment plays an important role in CEA due to its advantages of easy implementation and run-time robustness. However, existing embedding alignment methods haven't considered the problem of embedding distribution alignment which refers to the alignment of spatial shapes of embedding spaces. To this end, we present a new Adversarial Knowledge Embedding framework (AKE for short) that jointly learns the representation, mapping and adversarial modules in an end-to-end manner. By reducing the discrepancy of embedding distributions, AKE can approximately preserve an isomorphism between source and target embeddings. In addition, we introduce two new orthogonality constraints into mapping to obtain the self-consistency and numerical stability of transformation. Experiments on real-world datasets demonstrate that our method significantly outperforms state-of-the-art baselines.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	Proceedings - IEEE International Conference on Data Mining, ICDM
dc.relation.ispartof	IEEE International Conference on Data Mining
dc.relation.isbasedon	10.1109/ICDM.2019.00053
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Guiding cross-lingual entity alignment via adversarial knowledge embedding
dc.type	Conference Proceeding
utslib.citation.volume	2019-November
utslib.location.activity	Beijing, China
utslib.for	0801 Artificial Intelligence and Image Processing
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2021-04-14T19:46:56Z
pubs.finish-date	2019-11-11
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2019-11-08
pubs.volume	2019-November
dc.location	Piscataway, USA

Abstract:

© 2019 IEEE. Cross-lingual Entity Alignment (CEA) aims at identifying entities with their counterparts in different language knowledge graphs. Knowledge embedding alignment plays an important role in CEA due to its advantages of easy implementation and run-time robustness. However, existing embedding alignment methods haven't considered the problem of embedding distribution alignment which refers to the alignment of spatial shapes of embedding spaces. To this end, we present a new Adversarial Knowledge Embedding framework (AKE for short) that jointly learns the representation, mapping and adversarial modules in an end-to-end manner. By reducing the discrepancy of embedding distributions, AKE can approximately preserve an isomorphism between source and target embeddings. In addition, we introduce two new orthogonality constraints into mapping to obtain the self-consistency and numerical stability of transformation. Experiments on real-world datasets demonstrate that our method significantly outperforms state-of-the-art baselines.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/148105