Model Size Scaling in Zero-Shot Cross-Lingual Transfer on the TyDiQA Benchmark via Exact Match Accuracy

Multilingual BERT (mBERT), a language model pre-trained on large multilingual corpora, has impressive zero-shot cross-lingual transfer capabilities and performs surprisingly well on zero-shot POS tagging and Named Entity Recognition (NER), as well as on cross-lingual model transfer. At present, the mainstream methods to solve the cross-lingual downstream tasks are always using the last transformer layer's output of mBERT as the representation of linguistic information. In this work, we explore the complementary property of lower layers to the last transformer layer of mBERT. A feature aggregat

Research goal: What is the impact of model size (e.g., 100M, 1B, 10B parameters) on zero-shot cross-lingual transfer using the TyDiQA benchmark, measured by exact match accuracy?

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