Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering.
Pengfei LiGang LiuJinlong HeZixu ZhaoShenjun ZhongPublished in: MICCAI (1) (2023)
Keyphrases
- question answering
- natural language
- information retrieval
- information extraction
- natural language processing
- question classification
- cross language
- qa clef
- question answering systems
- passage retrieval
- visual information
- qa systems
- syntactic information
- named entities
- natural language questions
- open domain question answering
- relation extraction
- training set
- low level
- multi modal
- sentence retrieval
- visual features
- machine learning
- expert systems
- candidate answers
- high level
- answer extraction
- multimedia
- answering questions
- test set
- answer validation
- textual entailment recognition