Show simple item record

dc.contributor.authorPei, Shichao
dc.contributor.authorYu, Lu
dc.contributor.authorZhang, Xiangliang
dc.date.accessioned2020-03-02T11:38:51Z
dc.date.available2020-03-02T11:38:51Z
dc.date.issued2019-07-28
dc.identifier.citationPei, S., Yu, L., & Zhang, X. (2019). Improving Cross-lingual Entity Alignment via Optimal Transport. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. doi:10.24963/ijcai.2019/448
dc.identifier.doi10.24963/ijcai.2019/448
dc.identifier.urihttp://hdl.handle.net/10754/661838
dc.description.abstractCross-lingual entity alignment identifies entity pairs that share the same meanings but locate in different language knowledge graphs (KGs). The study in this paper is to address two limitations that widely exist in current solutions: 1) the alignment loss functions defined at the entity level serve well the purpose of aligning labeled entities but fail to match the whole picture of labeled and unlabeled entities in different KGs; 2) the translation from one domain to the other has been considered (e.g., X to Y by M1 or Y to X by M2). However, the important duality of alignment between different KGs (X to Y by M1 and Y to X by M2) is ignored. We propose a novel entity alignment framework (OTEA), which dually optimizes the entity-level loss and group-level loss via optimal transport theory. We also impose a regularizer on the dual translation matrices to mitigate the effect of noise during transformation. Extensive experimental results show that our model consistently outperforms the state-of-the-arts with significant improvements on alignment accuracy.
dc.description.sponsorshipThe research reported in this publication was supported by funding from King Abdullah University of Science and Technology (KAUST), under award number FCC/1/1976-19-01, and NSFC No. 61828302.
dc.publisherInternational Joint Conferences on Artificial Intelligence
dc.relation.urlhttps://www.ijcai.org/proceedings/2019/448
dc.relation.urlhttps://www.ijcai.org/proceedings/2019/0448.pdf
dc.rightsArchived with thanks to International Joint Conferences on Artificial Intelligence Organization
dc.titleImproving cross-lingual entity alignment via optimal transport
dc.typeConference Paper
dc.contributor.departmentComputer Science
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentMachine Intelligence & kNowledge Engineering Lab
dc.conference.date2019-08-10 to 2019-08-16
dc.conference.name28th International Joint Conference on Artificial Intelligence, IJCAI 2019
dc.conference.locationMacao, CHN
dc.eprint.versionPre-print
kaust.personPei, Shichao
kaust.personYu, Lu
kaust.personZhang, Xiangliang
kaust.grant.numberFCC/1/1976-19-01
refterms.dateFOA2020-03-02T13:13:16Z


Files in this item

Thumbnail
Name:
3778_OTEA.pdf
Size:
502.6Kb
Format:
PDF
Description:
Accepted manuscript

This item appears in the following Collection(s)

Show simple item record