Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence.
Abhinav PatilJaap JumeletYu Ying ChiuAndy LapastoraPeter ShenLexie WangClevis WillrichShane Steinert-ThrelkeldPublished in: CoRR (2024)
Keyphrases
- language model
- language modeling
- probabilistic model
- speech recognition
- document level
- n gram
- retrieval model
- language modelling
- query expansion
- information retrieval
- statistical language models
- document retrieval
- statistical machine translation
- multiword
- context sensitive
- query terms
- relevance model
- test collection
- vector space model
- passage retrieval
- query specific
- smoothing methods
- ad hoc information retrieval
- language models for information retrieval
- language model for information retrieval
- pseudo relevance feedback
- training set
- decision trees