Training Multilingual Pre-trained Language Model with Byte-level Subwords.
Junqiu WeiQun LiuYinpeng GuoXin JiangPublished in: CoRR (2021)
Keyphrases
- language model
- pre trained
- language modeling
- n gram
- query expansion
- training examples
- probabilistic model
- speech recognition
- retrieval model
- mixture model
- document retrieval
- information retrieval
- cross lingual
- ad hoc information retrieval
- training samples
- training set
- training data
- control signals
- query terms
- smoothing methods
- test collection
- supervised learning
- translation model
- query specific
- feature selection
- cross language
- machine learning