Stepwise Alignment for Constrained Language Model Policy Optimization.
Akifumi WachiThien Q. TranRei SatoTakumi TanabeYohei AkimotoPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- n gram
- language modelling
- information retrieval
- speech recognition
- document retrieval
- probabilistic model
- test collection
- query expansion
- retrieval model
- context sensitive
- smoothing methods
- statistical language models
- ad hoc information retrieval
- translation model
- mixture model
- word error rate
- query terms
- pseudo relevance feedback
- relevance model
- word segmentation
- multiword
- query specific
- vector space model
- statistical model