Effect of tokenization granularity for Turkish large language models.
Yigit Bekir KayaA. Cüneyd TantugPublished in: Intell. Syst. Appl. (2024)
Keyphrases
- language model
- n gram
- language modeling
- probabilistic model
- document retrieval
- speech recognition
- information retrieval
- language modelling
- test collection
- retrieval model
- statistical language models
- language model for information retrieval
- context sensitive
- pseudo relevance feedback
- smoothing methods
- query expansion
- vector space model
- word error rate
- ad hoc information retrieval
- query terms
- relevance model
- translation model
- document ranking
- error rate
- cross language information retrieval
- term dependencies
- named entities
- language models for information retrieval