Multilingual Language Model
Models trained on multiple languages simultaneously
Evolved from transformer architecture in attention-is-all-you-need
Examples: mBERT, XLM-R
Enables zero-shot cross-lingual transfer
References
#ml-notes
Models trained on multiple languages simultaneously
Evolved from transformer architecture in attention-is-all-you-need
Examples: mBERT, XLM-R
Enables zero-shot cross-lingual transfer
#ml-notes