Show simple item record

dc.contributor.authorHe, Fuzhen
dc.contributor.authorLi, Zhixu
dc.contributor.authorQiang, Yang
dc.contributor.authorLiu, An
dc.contributor.authorLiu, Guanfeng
dc.contributor.authorZhao, Pengpeng
dc.contributor.authorZhao, Lei
dc.contributor.authorZhang, Min
dc.contributor.authorChen, Zhigang
dc.date.accessioned2019-10-03T13:08:33Z
dc.date.available2019-10-03T13:08:33Z
dc.date.issued2019-04-24
dc.identifier.citationHe, F., Li, Z., Qiang, Y., Liu, A., Liu, G., Zhao, P., … Chen, Z. (2019). Unsupervised Entity Alignment Using Attribute Triples and Relation Triples. Lecture Notes in Computer Science, 367–382. doi:10.1007/978-3-030-18576-3_22
dc.identifier.doi10.1007/978-3-030-18576-3_22
dc.identifier.urihttp://hdl.handle.net/10754/656860
dc.description.abstractEntity alignment aims to find entities referring to the same real-world object across different knowledge graphs (KGs). Most existing works utilize the relations between entities contained in the relation triples with embedding-based approaches, but require a large number of training data. Some recent attempt works on using types of their attributes in attribute triples for measuring the similarity between entities across KGs. However, due to diverse expressions of attribute names and non-standard attribute values across different KGs, the information contained in attribute triples can not be fully used. To tackle the drawbacks of the existing efforts, we novelly propose an unsupervised entity alignment approach using both attribute triples and relation triples of KGs. Initially, we propose an interactive model to use attribute triples by performing entity alignment and attribute alignment alternately, which will generate a lot of high-quality aligned entity pairs. We then use these aligned entity pairs to train a relation embedding model such that we could use relation triples to further align the remaining entities. Lastly, we utilize a bivariate regression model to learn the respective weights of similarities measuring from the two aspects for a result combination. Our empirical study performed on several real-world datasets shows that our proposed method achieves significant improvements on entity alignment compared with state-of-the-art methods.
dc.description.sponsorshipThis research is partially supported by National Natural Science Foundation of China (Grant No. 61632016, 61572336, 61572335, 61772356), the Natural Science Research Project of Jiangsu Higher Education Institution (No. 17KJA520003, 18KJA520010), and the Open Program of Neusoft Corporation (No. SKLSAOP1801).
dc.publisherSpringer Nature
dc.relation.urlhttp://link.springer.com/10.1007/978-3-030-18576-3_22
dc.rightsArchived with thanks to Springer International Publishing
dc.subjectUnsupervised Entity Alignment
dc.subjectInteractive Model
dc.subjectBi-variate Regression Model
dc.subjectRelation Triples
dc.subjectAttribute Triples
dc.titleUnsupervised entity alignment using attribute triples and relation triples
dc.typeConference Paper
dc.contributor.departmentKing Abdullah University of Science and Technology, Jeddah, Saudi Arabia
dc.conference.date2019-04-22 to 2019-04-25
dc.conference.name24th International Conference on Database Systems for Advanced Applications, DASFAA 2019
dc.conference.locationChiang Mai, THA
dc.eprint.versionPost-print
dc.contributor.institutionInstitute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China
dc.contributor.institutionNeusoft Corporation, Shenyang, China
dc.contributor.institutionIFLYTEK Research, Suzhou, China
dc.contributor.institutionDepartment of Computing, Macquarie University, Sydney, Australia
kaust.personQiang, Yang
refterms.dateFOA2019-10-03T13:09:33Z
dc.date.published-online2019-04-24
dc.date.published-print2019


Files in this item

Thumbnail
Name:
Unsupervised Entity Alignment using Attribute Triples and Relation Triples.pdf
Size:
362.0Kb
Format:
PDF
Description:
Accepted manuscript

This item appears in the following Collection(s)

Show simple item record