Why do small language models underperform? Studying Language Model Saturation via the Softmax Bottleneck.
Nathan GodeyÉric de la ClergerieBenoît SagotPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- document retrieval
- probabilistic model
- information retrieval
- retrieval model
- query expansion
- speech recognition
- context sensitive
- language modelling
- mixture model
- ad hoc information retrieval
- test collection
- smoothing methods
- vector space model
- statistical language models
- language models for information retrieval
- query terms
- information retrieval systems
- pseudo relevance feedback
- term dependencies
- document length
- word error rate