Language Model Tokenizers Introduce Unfairness Between Languages.
Aleksandar PetrovEmanuele La MalfaPhilip H. S. TorrAdel BibiPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- statistical machine translation
- speech recognition
- document retrieval
- information retrieval
- probabilistic model
- cross lingual
- retrieval model
- query expansion
- language modelling
- vector space model
- context sensitive
- test collection
- language independent
- ad hoc information retrieval
- mixture model
- smoothing methods
- relevance model
- language model for information retrieval
- translation model
- document ranking
- word error rate
- query terms
- language models for information retrieval
- bayesian networks