Multilingual Pre-training for Zero-Shot Cross-Lingual Retrieval on MIRACL

Using task-specific pre-training and leveraging cross-lingual transfer are two of the most popular ways to handle code-switched data. In this paper, we aim to compare the effects of both for the task of sentiment analysis. We work with two Dravidian Code-Switched languages - Tamil-Engish and Malayalam-English and four different BERT based models. We compare the effects of task-specific pre-training and cross-lingual transfer and find that task-specific pre-training results in superior zero-shot and supervised performance when compared to performance achieved by leveraging cross-lingual transfe

Research goal: Can incorporating multilingual pre-training objectives improve zero-shot cross-lingual retrieval performance on MIRACL when trained on artificially code-switched data, and how does this compare to using back-translated data, as evaluated by precision@k and MAP scores?

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