XLM-R Model Scaling for Zero-Shot Cross-Lingual Sentiment Transfer in Distant Language Pairs

This research explores the applicability of cross-lingual transfer learning from English to Japanese and Indonesian using the XLM-R pre-trained model. The results are compared with several previous works, either by models using a similar zero-shot approach or a fully-supervised approach, to provide an overview of the zero-shot transfer learning approach's capability using XLM-R in comparison with existing models. Our models achieve the best result in one Japanese dataset and comparable results in other datasets in Japanese and Indonesian languages without being trained using the target languag

Research goal: What is the effect of increasing the model size of XLM-R on zero-shot cross-lingual transfer accuracy for distant language pairs in sentiment classification tasks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10.