On the Impact of the Vocabulary for Domain-Adaptive Pretraining of Clinical Language Models.
Anastasios LamproudisAron HenrikssonPublished in: BIOSTEC (Selected Papers) (2022)
Keyphrases
- language model
- language modeling
- n gram
- statistical language models
- probabilistic model
- information retrieval
- spoken term detection
- out of vocabulary
- test collection
- query expansion
- retrieval model
- language modelling
- document retrieval
- speech recognition
- query terms
- language model for information retrieval
- context sensitive
- vector space model
- document ranking
- relevance model
- ad hoc information retrieval
- term dependencies
- pseudo relevance feedback
- translation model
- word error rate
- decision trees
- keywords
- statistical language modeling
- machine learning
- natural language processing