An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training.
Kristjan ArumaeQing SunParminder BhatiaPublished in: CoRR (2020)
Keyphrases
- language model
- multi domain
- language modeling
- n gram
- document retrieval
- probabilistic model
- context sensitive
- retrieval model
- speech recognition
- test collection
- smoothing methods
- query expansion
- ad hoc information retrieval
- training set
- language modelling
- information retrieval
- mixture model
- cross domain
- query terms
- domain specific
- general purpose
- text mining