Biomedical Language Models are Robust to Sub-optimal Tokenization.
Bernal Jiménez GutiérrezHuan SunYu SuPublished in: CoRR (2023)
Keyphrases
- language model
- n gram
- language modeling
- language modelling
- biomedical text
- statistical language models
- query expansion
- information retrieval
- speech recognition
- document retrieval
- retrieval model
- probabilistic model
- pseudo relevance feedback
- ad hoc information retrieval
- smoothing methods
- context sensitive
- test collection
- information extraction
- language models for information retrieval
- vector space model
- biomedical information retrieval
- cross lingual
- relevance model
- language model for information retrieval
- biomedical literature
- passage retrieval
- document ranking
- okapi bm