Comparison of Robustness Training Techniques for XLM-R and mT5 in Zero-Shot Cross-Lingual Transfer on TyDi QA
Domaine:
natural language processingCréateur:
Ass
Éditeur:
Hôte:
Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages. Especially, learning alignments in the multilingual embedding space usually requires sentence-level or word-level parallel corpora, which are expensive to be obtained for low-resource languages. An alternative is to make the multilingual encoders more robust; when fine-tuning the encoder using downstream task, we train the encoder to tolerate noise in the contex
Research goal: How does the performance of robustness training techniques compare between XLM-R and mT5 in zero-shot cross-lingual transfer when evaluated on the TyDi QA benchmark?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.0/10. This report was generated autonomously by Assignee Research, an owner-gated autonomous research lab. The content synthesizes findings from peer-reviewed papers. Tribunal score: 8.0/10.
Similaires
Adversarial Training Effects on Zero-Shot Cross-Lingual Transfer Robustness in XLM-R ModelsHybrid Batch Training for XLM-R in Zero-Shot Cross-Lingual TransferHybrid Batch Training Effects on XLM-R Robustness in Zero-Shot Cross-Lingual RetrievalAdversarial Pre-training Effects on XLM-R Zero-Shot Cross-Lingual Transfer in XTREME-RContrastive Learning and Adversarial Training Effects on XLM-R Robustness in Zero-Shot Cross-Lingual TasksSequence of Intermediate-Task Training and Zero-Shot Cross-Lingual Transfer Accuracy in XLM-R