Multilingual Pre-Training Data Imbalance and Zero-Shot Retrieval Performance in Contrastive Learning 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: What is the impact of multilingual pre-training data imbalance on the zero-shot retrieval performance of contrastive learning models evaluated on the Multilingual Natural Language Inference (MNLI) benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10.