Cross-lingual transfer is a popular approach to increase the amount of training data for NLP tasks in a low-resource context. However, the best strategy to decide which cross-lingual data to include is unclear. Prior research often focuses on a small set of languages from a few language families or a single task. It is still an open question how these findings extend to a wider variety of languages and tasks. In this work, we contribute to this question by analyzing cross-lingual transfer for 263 languages from a wide variety of language families. Moreover, we include three popular NLP tasks in our analysis: POS-tagging, dependency parsing, and topic classification. Our findings indicate that the effect of linguistic similarity on transfer performance depends on a range of factors: the NLP task, the (mono- or multilingual) input representations, and the definition of linguistic similarity.
- † Work done while at Apple
- ‡ LMU Munich
- § Munich Center for Machine Learning