Leveraging type descriptions for zero-shot named entity recognition and classification
| cam.orpheus.success | Mon Nov 15 07:30:18 GMT 2021 - Embargo updated | |
| dc.contributor.author | Aly, R | |
| dc.contributor.author | Vlachos, A | |
| dc.contributor.author | McDonald, R | |
| dc.contributor.orcid | Vlachos, Andreas [0000-0003-2123-5071] | |
| dc.date.accessioned | 2021-11-09T00:31:14Z | |
| dc.date.available | 2021-11-09T00:31:14Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | A 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.identifier.doi | 10.17863/CAM.77922 | |
| dc.identifier.isbn | 9781954085527 | |
| dc.identifier.uri | https://www.repository.cam.ac.uk/handle/1810/330478 | |
| dc.language.iso | eng | |
| dc.publisher | Association for Computational Linguistics | |
| dc.publisher.url | http://dx.doi.org/10.18653/v1/2021.acl-long.120 | |
| dc.rights | Attribution 4.0 International | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.title | Leveraging type descriptions for zero-shot named entity recognition and classification | |
| dc.type | Conference Object | |
| dcterms.dateAccepted | 2021-05-05 | |
| prism.endingPage | 1528 | |
| prism.publicationDate | 2021 | |
| prism.publicationName | ACL-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.startingPage | 1516 | |
| pubs.conference-finish-date | 2021-08 | |
| pubs.conference-name | Proceedings 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-date | 2021-08 | |
| pubs.funder-project-id | European Commission Horizon 2020 (H2020) ERC (865958) | |
| pubs.funder-project-id | Engineering and Physical Sciences Research Council (EP/R021643/2) | |
| rioxxterms.licenseref.startdate | 2021-01-01 | |
| rioxxterms.licenseref.uri | http://www.rioxx.net/licenses/all-rights-reserved | |
| rioxxterms.type | Conference Paper/Proceeding/Abstract | |
| rioxxterms.version | VoR | |
| rioxxterms.versionofrecord | 10.18653/v1/2021.acl-long.120 |
Files
Original bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- 2021.acl-long.120.pdf
- Size:
- 431.83 KB
- Format:
- Adobe Portable Document Format
- Description:
- Published version
- Licence
- https://creativecommons.org/licenses/by/4.0/
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- DepositLicenceAgreementv2.1.pdf
- Size:
- 150.9 KB
- Format:
- Adobe Portable Document Format