DA-Net: A Disentangled and Adaptive Network for Multi-Source Cross-Lingual Transfer Learning

arXiv:2403.04158v1 Announce Type: new
Abstract: Multi-Source cross-lingual transfer learning deals with the transfer of task knowledge from multiple labelled source languages to an unlabeled target language under the language shift. Existing methods typically focus on weighting the predictions produced by language-specific classifiers of different sources that follow a shared encoder. However, all source languages share the same encoder, which is updated by all these languages. The extracted representations inevitably contain different source languages' information, which may disturb the learning of …

abstract arxiv classifiers cross-lingual cs.ai cs.cl deals focus knowledge language languages multiple network predictions shift transfer transfer learning type