What's left can't be right - The remaining positional incompetence of contrastive vision-language models.
Nils HoehingEllen RusheAnthony VentresquePublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- speech recognition
- information retrieval
- probabilistic model
- n gram
- statistical language models
- document retrieval
- query expansion
- test collection
- retrieval model
- context sensitive
- language modelling
- computer vision
- smoothing methods
- language model for information retrieval
- ad hoc information retrieval
- document length
- document ranking
- relevance model
- pseudo relevance feedback
- query specific
- passage retrieval
- word error rate
- search engine