Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Input Representations Matter Apple Machine Learning Research
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… Read More »Analyzing the Effect of Linguistic Similarity on Cross-Lingual Transfer: Tasks and Input Representations Matter Apple Machine Learning Research