Positional Attention Guided Transformer-Like Architecture for Visual Question Answering.
Aihua MaoZhi YangKen LinJun XuanYong-Jin LiuPublished in: IEEE Trans. Multim. (2023)
Keyphrases
- question answering
- natural language processing
- information retrieval
- information extraction
- question classification
- natural language questions
- named entities
- natural language
- syntactic information
- open domain question answering
- cross language
- question answering systems
- low level
- visual information
- relation extraction
- passage retrieval
- sentence retrieval
- multi modal
- answer extraction
- qa clef
- answer validation
- answering questions
- co occurrence
- speech transcripts
- data mining