Show simple item record

dc.contributor.authorBuck, G
dc.contributor.authorVlachos, Andreas
dc.date.accessioned2021-12-10T00:30:32Z
dc.date.available2021-12-10T00:30:32Z
dc.date.issued2021-01-01
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/331317
dc.description.abstractWord embedding learning methods require a large number of occurrences of a word to accurately learn its embedding. However, out-of-vocabulary (OOV) words which do not appear in the training corpus emerge frequently in the smaller downstream data. Recent work formulated OOV embedding learning as a few-shot regression problem and demonstrated that meta-learning can improve results obtained. However, the algorithm used, model-agnostic meta-learning (MAML) is known to be unstable and perform worse when a large number of gradient steps are used for parameter updates. In this work, we propose the use of Leap, a meta-learning algorithm which leverages the entire trajectory of the learning process instead of just the beginning and the end points, and thus ameliorates these two issues. In our experiments on a benchmark OOV embedding learning dataset and in an extrinsic evaluation, Leap performs comparably or better than MAML. We go on to examine which contexts are most beneficial to learn an OOV embedding from, and propose that the choice of contexts may matter more than the meta-learning employed.
dc.rightsAll Rights Reserved
dc.rights.urihttp://www.rioxx.net/licenses/all-rights-reserved
dc.subjectcs.CL
dc.subjectcs.CL
dc.titleTrajectory-based meta-learning for out-of-vocabulary word embedding learning
dc.typeArticle
dc.publisher.departmentDepartment of Computer Science And Technology
dc.date.updated2021-12-08T11:04:15Z
prism.endingPage155
prism.publicationDate2021
prism.publicationNameAdapt-NLP 2021 - 2nd Workshop on Domain Adaptation for NLP, Proceedings
prism.startingPage146
dc.identifier.doi10.17863/CAM.78765
rioxxterms.versionAM
dc.contributor.orcidVlachos, Andreas [0000-0003-2123-5071]
rioxxterms.typeJournal Article/Review
cam.orpheus.counter7*
cam.depositDate2021-12-08
pubs.licence-identifierapollo-deposit-licence-2-1
pubs.licence-display-nameApollo Repository Deposit Licence Agreement
rioxxterms.freetoread.startdate2100-01-01


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record