“…In contrast to these tasks, which have seen much cross-lingual attention (Plank et al, 2016;Bjerva, 2017;Kementchedjhieva et al, 2018;de Lhoneux et al, 2018), there has been relatively little work on cross-lingual NLU, partly due to lack of benchmark datasets. Existing work has mainly been focused on NLI (Agic and Schluter, 2018;Conneau et al, 2018;Zhao et al, 2020), and to a lesser degree on RE (Faruqui and Kumar, 2015;Verga et al, 2016) and QA (Abdou et al, 2019;Lewis et al, 2020). Previous research generally reports that cross-lingual learning is challenging and that it is hard to beat a machine translation baseline (e.g., Conneau et al (2018)).…”