On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting.
Tomasz KorbakHady ElsaharGermán KruszewskiMarc DymetmanPublished in: NeurIPS (2022)
Keyphrases
- language model
- fine tuning
- reinforcement learning
- language modeling
- document retrieval
- n gram
- speech recognition
- retrieval model
- language modelling
- query expansion
- test collection
- fine tuned
- information retrieval
- probabilistic model
- fine tune
- statistical language models
- mixture model
- ad hoc information retrieval
- smoothing methods
- context sensitive
- query terms
- language models for information retrieval
- language model for information retrieval
- okapi bm
- relevance model
- information retrieval systems
- query specific
- word error rate
- cross lingual
- translation model
- passage retrieval
- pseudo relevance feedback
- vector space model
- web search
- knn
- bayesian networks