Show simple item record

dc.contributor.authorAly, R
dc.contributor.authorVlachos, Andreas
dc.contributor.authorMcDonald, R
dc.date.accessioned2021-11-09T00:31:14Z
dc.date.available2021-11-09T00:31:14Z
dc.date.issued2021
dc.identifier.isbn9781954085527
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/330478
dc.description.abstractA common issue in real-world applications of named entity recognition and classification (NERC) is the absence of annotated data for target entity classes during training. Zeroshot learning approaches address this issue by learning models that can transfer information from observed classes in the training data to unseen classes. This paper presents the first approach for zero-shot NERC, introducing a novel architecture that leverage the fact that textual descriptions for many entity classes occur naturally. Our architecture addresses the zero-shot NERC specific challenge that the not-an-entity class is not well defined, since different entity classes are considered in training and testing. For evaluation, we adapt two datasets, OntoNotes and MedMentions, emulating the difficulty of real-world zero-shot learning by testing models on the rarest entity classes. Our proposed approach outperforms baselines adapted from machine reading comprehension and zero-shot text classification. Furthermore, we assess the effect of different class descriptions for this task.
dc.publisherAssociation for Computational Linguistics
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleLeveraging type descriptions for zero-shot named entity recognition and classification
dc.typeConference Object
prism.endingPage1528
prism.publicationDate2021
prism.publicationNameACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference
prism.startingPage1516
dc.identifier.doi10.17863/CAM.77922
dcterms.dateAccepted2021-05-05
rioxxterms.versionofrecord10.18653/v1/2021.acl-long.120
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2021-01-01
dc.contributor.orcidVlachos, Andreas [0000-0003-2123-5071]
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.funder-project-idEuropean Commission Horizon 2020 (H2020) ERC (865958)
pubs.conference-nameProceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
pubs.conference-start-date2021-08
cam.orpheus.successMon Nov 15 07:30:18 GMT 2021 - Embargo updated
pubs.conference-finish-date2021-08
rioxxterms.freetoread.startdate2100-01-01


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's licence is described as Attribution 4.0 International