On the importance of pre-training data volume for compact language models.
Vincent MicheliMartin d'HoffschmidtFrançois FleuretPublished in: CoRR (2020)
Keyphrases
- language model
- training data
- language modeling
- n gram
- speech recognition
- document retrieval
- probabilistic model
- query expansion
- language modelling
- information retrieval
- test collection
- retrieval model
- context sensitive
- decision trees
- statistical language models
- classification accuracy
- training set
- smoothing methods
- pseudo relevance feedback
- ad hoc information retrieval
- vector space model
- machine learning
- language models for information retrieval
- language model for information retrieval
- supervised learning
- document ranking
- term dependencies
- speech signal
- query terms