Improving the Performance of Large Language Models by Domain-Specific Pre-Training on Clinical Documents.
Bryan D. SteitzCharreau BellJesse Spencer-SmithAdam WrightPublished in: AMIA (2022)
Keyphrases
- language model
- domain specific
- document retrieval
- ad hoc information retrieval
- information retrieval
- document ranking
- query terms
- vector space model
- language modeling
- document representation
- language modeling approaches
- document level
- statistical language models
- query expansion
- n gram
- retrieval model
- relevance model
- passage retrieval
- document length
- relevant documents
- speech recognition
- probabilistic model
- pseudo feedback
- query specific
- multiword
- language modelling
- pseudo relevance feedback
- ir models
- test collection
- retrieved documents
- term dependencies
- expert finding
- probabilistic retrieval models
- document collections
- retrieval effectiveness
- information retrieval systems
- text documents
- term frequency
- tf idf
- text retrieval
- smoothing methods
- context sensitive
- language modeling framework
- keywords
- language models for information retrieval
- document clustering
- expert search
- sentence retrieval
- question answering
- user queries
- text mining
- term weighting
- natural language processing
- relevance assessments