VQAMix: Conditional Triplet Mixup for Medical Visual Question Answering.
Haifan GongGuanqi ChenMingzhi MaoZhen LiGuanbin LiPublished in: IEEE Trans. Medical Imaging (2022)
Keyphrases
- question answering
- information retrieval
- question classification
- information extraction
- natural language questions
- natural language processing
- visual information
- natural language
- syntactic information
- qa clef
- named entities
- cross language
- open domain question answering
- answering questions
- answer extraction
- question answering systems
- relation extraction
- visual features
- search engine
- qa systems
- candidate answers
- low level
- machine learning
- answer validation
- data mining