Parts of Speech-Grounded Subspaces in Vision-Language Models.
James OldfieldChristos TzelepisYannis PanagakisMihalis NicolaouIoannis PatrasPublished in: NeurIPS (2023)
Keyphrases
- language model
- speech recognition
- word error rate
- language modeling
- probabilistic model
- spoken term detection
- information retrieval
- document retrieval
- speech signal
- n gram
- automatic speech recognition
- query expansion
- retrieval model
- test collection
- smoothing methods
- pseudo relevance feedback
- mixture model
- language modelling
- low dimensional
- out of vocabulary
- context sensitive
- ad hoc information retrieval
- high dimensional data
- statistical language models
- relevance model
- high dimensional
- audio visual
- vector space model
- handwriting recognition
- document ranking
- query specific
- search engine
- feature space
- query terms