AMBERT: A Pre-trained Language Model with Multi-Grained Tokenization.
Xinsong ZhangHang LiPublished in: CoRR (2020)
Keyphrases
- language model
- pre trained
- n gram
- language modeling
- information retrieval
- document retrieval
- probabilistic model
- speech recognition
- query expansion
- retrieval model
- training examples
- context sensitive
- training data
- test collection
- mixture model
- named entities
- pseudo relevance feedback
- relevance model
- ad hoc information retrieval
- query terms
- control signals
- translation model