XLM is a Transformer based architecture that is pre-trained using one of three language modelling objectives:
- Causal Language Modeling - models the probability of a word given the previous words in a sentence.
- Masked Language Modeling - the masked language modeling objective of BERT.
- Translation Language Modeling - a (new) translation language modeling objective for improving cross-lingual pre-training.
The authors find that both the CLM and MLM approaches provide strong cross-lingual features that can be used for pretraining models.