Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation.
François RemyPieter DelobelleBettina BerendtKris DemuynckThomas DemeesterPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- speech recognition
- n gram
- probabilistic model
- information retrieval
- document retrieval
- retrieval model
- context sensitive
- language modelling
- vector space model
- statistical language models
- query expansion
- test collection
- language models for information retrieval
- pseudo relevance feedback
- relevance model
- term dependencies
- document length
- statistical language modeling