%0 Conference Proceedings %T When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer %A Deshpande, Ameet %A Talukdar, Partha %A Narasimhan, Karthik %Y Carpuat, Marine %Y de Marneffe, Marie-Catherine %Y Meza Ruiz, Ivan Vladimir %S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies %D 2022 %8 July %I Association for Computational Linguistics %C Seattle, United States %F deshpande-etal-2022-bert %X While recent work on multilingual language models has demonstrated their capacity for cross-lingual zero-shot transfer on downstream tasks, there is a lack of consensus in the community as to what shared properties between languages enable such transfer. Analyses involving pairs of natural languages are often inconclusive and contradictory since languages simultaneously differ in many linguistic aspects. In this paper, we perform a large-scale empirical study to isolate the effects of various linguistic properties by measuring zero-shot transfer between four diverse natural languages and their counterparts constructed by modifying aspects such as the script, word order, and syntax. Among other things, our experiments show that the absence of sub-word overlap significantly affects zero-shot transfer when languages differ in their word order, and there is a strong correlation between transfer performance and word embedding alignment between languages (e.g., ρ_s=0.94 on the task of NLI). Our results call for focus in multilingual models on explicitly improving word embedding alignment between languages rather than relying on its implicit emergence. %R 10.18653/v1/2022.naacl-main.264 %U https://aclanthology.org/2022.naacl-main.264 %U https://doi.org/10.18653/v1/2022.naacl-main.264 %P 3610-3623