SEQUENCE MIXUP FOR ZERO-SHOT CROSS-LINGUAL PART-OF-SPEECH TAGGING
Keywords: natural language processing, multilingual learning, mixup
TL;DR: We explore interpolative data augmentation for POS tagging
Abstract: There have been efforts in cross-lingual transfer learning for various tasks. We present an approach utilizing an interpolative data augmentation method, Mixup, to improve the generalizability of models for part-of-speech tagging trained on a source language, improving its performance on unseen target languages. Through experiments on ten languages with diverse structures and language roots, we put forward its applicability for downstream zero-shot cross-lingual tasks.
Submission Number: 129
Loading