MLeVLM: Improve Multi-level Progressive Capabilities based on Multimodal Large Language Model for Medical Visual Question Answering.
Dexuan XuYanyuan ChenJieyi WangYue HuangHanpin WangZhi JinHongxing WangWeihua YueJing HeHang LiYu HuangPublished in: ACL (Findings) (2024)
Keyphrases
- question answering
- language model
- passage retrieval
- information retrieval
- sentence retrieval
- language modeling
- document retrieval
- n gram
- retrieval model
- question classification
- natural language processing
- cross language
- query expansion
- probabilistic model
- speech recognition
- test collection
- information extraction
- visual features
- query terms
- relevance model
- named entities
- visual information
- vector space model
- multi modal
- image retrieval
- natural language
- error rate