Sun, K., Zhang, R., Mensah, S. orcid.org/0000-0003-0779-5574 et al. (2 more authors) (2022) A transformational biencoder with in-domain negative sampling for zero-shot entity linking. In: Findings of the Association for Computational Linguistics: ACL 2022. The 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), 22-27 May 2022, Dublin, Ireland. Association for Computational Linguistics , pp. 1449-1458. ISBN 9781955917254
Abstract
Recent interest in entity linking has focused in the zero-shot scenario, where at test time the entity mention to be labelled is never seen during training, or may belong to a different domain from the source domain. Current work leverage pre-trained BERT with the implicit assumption that it bridges the gap between the source and target domain distributions. However, fine-tuned BERT has a considerable underperformance at zero-shot when applied in a different domain. We solve this problem by proposing a Transformational Biencoder that incorporates a transformation into BERT to perform a zero-shot transfer from the source domain during training. As like previous work, we rely on negative entities to encourage our model to discriminate the golden entities during training. To generate these negative entities, we propose a simple but effective strategy that takes the domain of the golden entity into perspective. Our experimental results on the benchmark dataset Zeshel show effectiveness of our approach and achieve new state-of-the-art.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2022 Association for Computational Linguistics. This paper licensed on a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/). |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Funding Information: | Funder Grant number The Leverhulme Trust RPG-2020-148 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 26 Aug 2022 12:39 |
Last Modified: | 26 Aug 2022 12:39 |
Status: | Published |
Publisher: | Association for Computational Linguistics |
Refereed: | Yes |
Identification Number: | 10.18653/v1/2022.findings-acl.114 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:190346 |