BiodivBERT: a Pre-Trained Language Model for the Biodiversity Domain.
Nora AbdelmageedFelicitas LöfflerBirgitta König-RiesPublished in: SWAT4HCLS (2023)
Keyphrases
- language model
- pre trained
- language modeling
- n gram
- document retrieval
- probabilistic model
- speech recognition
- information retrieval
- mixture model
- query expansion
- retrieval model
- context sensitive
- test collection
- training data
- language modelling
- ad hoc information retrieval
- pairwise
- support vector
- relevance model
- machine learning