Scaling WEAM Pre-training to 100+ Languages for Cross-Domain Zero-Shot Robustness

Multilingual pre-trained models have achieved remarkable performance on cross-lingual transfer learning. Some multilingual models such as mBERT, have been pre-trained on unlabeled corpora, therefore the embeddings of different languages in the models may not be aligned very well. In this paper, we aim to improve the zero-shot cross-lingual transfer performance by proposing a pre-training task named Word-Exchange Aligning Model (WEAM), which uses the statistical alignment information as the prior knowledge to guide cross-lingual word prediction. We evaluate our model on multilingual machine rea

Research goal: Does scaling the WEAM pre-training task to 100+ languages improve robustness in cross-domain zero-shot transfer, as evaluated by accuracy on MLQA and TyDiQA benchmarks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.9/10.