Cross-lingual zero-shot transfer via semantic and synthetic representation learning

摘要: (57) ABSTRACT A computer-implemented method is provided for cross lingual transfer. The method includes randomly masking a source corpus and a target corpus to obtain a masked source corpus and a masked target corpus. The method further includes tokenizing, by pretrained Natural Language Pro cessing (NLP) models, the masked source corpus and the masked target corpus to obtain source tokens and target tokens. The method also includes transforming the source tokens and the target tokens into a source dependency parsing tree and a target dependency parsing tree. The method additionally includes inputting the source depen dency parsing tree and the target dependency parsing tree into a graph encoder pretrained on a translation language modeling task to extract common language information for transfer. The method further includes fine-tuning the graph encoder and a down-stream network …