Zero-shot Cross-lingual Retrieval Performance in Code-switched vs. Parallel Corpus Models

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: How does the zero-shot cross-lingual retrieval performance of models trained on code-switched data compare to models fine-tuned on parallel corpora, as measured by accuracy on XNLI and MLQA?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.