InfoVisDial: An Informative Visual Dialogue Dataset by Bridging Large Multimodal and Language Models.
Bingbing WenZhengyuan YangJianfeng WangZhe GanBill HoweLijuan WangPublished in: CoRR (2023)
Keyphrases
- language model
- language modeling
- n gram
- speech recognition
- document retrieval
- information retrieval
- retrieval model
- language modelling
- probabilistic model
- statistical language models
- query expansion
- test collection
- visual information
- language models for information retrieval
- ad hoc information retrieval
- vector space model
- low level
- visual features
- language model for information retrieval
- document ranking
- query terms
- translation model
- text retrieval
- multi modal
- term dependencies
- smoothing methods
- visual data
- context sensitive