On the N-gram Approximation of Pre-trained Language Models.
Aravind KrishnanJesujoba O. AlabiDietrich KlakowPublished in: INTERSPEECH (2023)
Keyphrases
- n gram
- language model
- pre trained
- language modeling
- language modelling
- training data
- document retrieval
- language independent
- test collection
- bag of words
- query expansion
- information retrieval
- retrieval model
- probabilistic model
- speech recognition
- training examples
- query terms
- word segmentation
- text classification
- document ranking
- machine learning
- statistical model
- pseudo relevance feedback
- out of vocabulary
- control signals
- relevance model