Pseudo-OOD training for robust language models.
Dhanasekar SundararamanNikhil MehtaLawrence CarinPublished in: CoRR (2022)
Keyphrases
- language model
- language modeling
- n gram
- probabilistic model
- retrieval model
- statistical language models
- language modelling
- document retrieval
- context sensitive
- speech recognition
- test collection
- information retrieval
- query expansion
- formal specification
- language models for information retrieval
- language model for information retrieval
- dynamic aspects
- translation model
- relevance model
- training set
- document ranking
- smoothing methods
- pseudo relevance feedback
- vector space model
- web search
- case study