Zero-shot Cross-Language Transfer of Monolingual Entity Linking Models

Elliot Schumacher, James Mayfield, Mark Dredze


Abstract
Most entity linking systems, whether mono or multilingual, link mentions to a single English knowledge base. Few have considered linking non-English text to a non-English KB, and therefore, transferring an English entity linking model to both a new document and KB language. We consider the task of zero-shot cross-language transfer of entity linking systems to a new language and KB. We find that a system trained with multilingual representations does reasonably well, and propose improvements to system training that lead to improved recall in most datasets, often matching the in-language performance. We further conduct a detailed evaluation to elucidate the challenges of this setting.
Anthology ID:
2022.mrl-1.4
Volume:
Proceedings of the The 2nd Workshop on Multi-lingual Representation Learning (MRL)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Venue:
MRL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
38–51
Language:
URL:
https://aclanthology.org/2022.mrl-1.4
DOI:
10.18653/v1/2022.mrl-1.4
Bibkey:
Cite (ACL):
Elliot Schumacher, James Mayfield, and Mark Dredze. 2022. Zero-shot Cross-Language Transfer of Monolingual Entity Linking Models. In Proceedings of the The 2nd Workshop on Multi-lingual Representation Learning (MRL), pages 38–51, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Zero-shot Cross-Language Transfer of Monolingual Entity Linking Models (Schumacher et al., MRL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2022.mrl-1.4.pdf