Repository logo
 

A survey of cross-lingual word embedding models

cam.issuedOnline2019-08-12
dc.contributor.authorRuder, S
dc.contributor.authorVulić, I
dc.contributor.authorSøgaard, A
dc.date.accessioned2018-10-03T04:45:38Z
dc.date.available2018-10-03T04:45:38Z
dc.date.issued2019
dc.description.abstract<jats:p>Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In this survey, we provide a comprehensive typology of cross-lingual word embedding models. We compare their data requirements and objective functions. The recurring theme of the survey is that many of the models presented in the literature optimize for the same objectives, and that seemingly different models are often equivalent, modulo optimization strategies, hyper-parameters, and such. We also discuss the different ways cross-lingual word embeddings are evaluated, as well as future challenges and research horizons.</jats:p>
dc.identifier.doi10.17863/CAM.30462
dc.identifier.eissn1943-5037
dc.identifier.issn1076-9757
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/283100
dc.language.isoeng
dc.publisherAI Access Foundation
dc.publisher.urlhttp://dx.doi.org/10.1613/jair.1.11640
dc.subject4603 Computer Vision and Multimedia Computation
dc.subject46 Information and Computing Sciences
dc.subject4602 Artificial Intelligence
dc.subject4611 Machine Learning
dc.titleA survey of cross-lingual word embedding models
dc.typeArticle
dcterms.dateAccepted2018-05-02
prism.endingPage631
prism.publicationDate2019
prism.publicationNameJournal of Artificial Intelligence Research
prism.startingPage569
prism.volume65
pubs.funder-project-idEuropean Research Council (648909)
rioxxterms.licenseref.startdate2019-01-01
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.typeJournal Article/Review
rioxxterms.versionAM
rioxxterms.versionofrecord10.1613/JAIR.1.11640

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
survey-cross-lingual.pdf
Size:
1.42 MB
Format:
Adobe Portable Document Format
Description:
Accepted version
Licence
http://www.rioxx.net/licenses/all-rights-reserved
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
DepositLicenceAgreementv2.1.pdf
Size:
150.9 KB
Format:
Adobe Portable Document Format