Pre-training mT5 with Multilingual Intermediate Tasks for Zero-Shot Cross-Lingual Transfer Performance on XTREME-Z

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: Does pre-training mT5 with a mix of English and multilingual intermediate tasks improve zero-shot cross-lingual transfer performance on XTREME-Z compared to English-only intermediate tasks, and how does this compare across different linguistic domains via F1 score comparisons?

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