Intra-Modality Feature Interaction Using Self-attention for Visual Question Answering.
Huan ShaoYunlong XuYi JiJianyu YangChunping LiuPublished in: ICONIP (5) (2019)
Keyphrases
- question answering
- information retrieval
- qa clef
- question classification
- information extraction
- natural language processing
- syntactic information
- passage retrieval
- multi modal
- named entities
- open domain question answering
- cross language
- feature vectors
- visual information
- visual features
- natural language
- sentence retrieval
- relation extraction
- semantic roles
- image features
- natural language questions
- feature set
- candidate answers
- visual data
- qa systems
- answer validation
- data mining