%0 Conference Proceedings %T Entity Linking in 100 Languages %A Botha, Jan A. %A Shan, Zifei %A Gillick, Daniel %Y Webber, Bonnie %Y Cohn, Trevor %Y He, Yulan %Y Liu, Yang %S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) %D 2020 %8 November %I Association for Computational Linguistics %C Online %F botha-etal-2020-entity %X 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. %R 10.18653/v1/2020.emnlp-main.630 %U https://aclanthology.org/2020.emnlp-main.630 %U https://doi.org/10.18653/v1/2020.emnlp-main.630 %P 7833-7845