We propose a new formulation for multilingual entity linking, where language-specific mentions resolve to a language-agnostic Knowledge Base. We train a dual encoder in this new setting, building on prior work with improved feature representation, negative mining, and an auxiliary entity-pairing task, to obtain a single entity retrieval model that covers 100+ languages and 20 million entities. The model outperforms state-of-the-art results from a far more limited cross-lingual linking task. Rare entities and low-resource languages pose challenges at this large-scale, so we advocate for an increased focus on zero- and few-shot evaluation. To this end, we provide Mewsli-9, a large new multilingual dataset matched to our setting, and show how frequency-based analysis provided key insights for our model and training enhancements.
CITATION STYLE
Botha, J. A., Shan, Z., & Gillick, D. (2020). Entity linking in 100 languages. In EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 7833–7845). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2020.emnlp-main.630
Mendeley helps you to discover research relevant for your work.