GViG: Generative Visual Grounding Using Prompt-Based Language Modeling for Visual Question Answering.
Yi-Ting LiYing-Jia LinChia-Jen YehChun-Yi LinHung-Yu KaoPublished in: PAKDD (6) (2024)
Keyphrases
- question answering
- language modeling
- sentence retrieval
- information retrieval
- language model
- visual features
- natural language
- cross language
- cross lingual
- natural language processing
- query expansion
- named entities
- machine learning
- information extraction
- probabilistic model
- wordnet
- generative model
- information retrieval systems
- retrieval model
- web search
- question answering systems
- feature selection
- natural language questions