Multimodal Bi-direction Guided Attention Networks for Visual Question Answering.
Linqin CaiNuoying XuHang TianKejia ChenHaodu FanPublished in: Neural Process. Lett. (2023)
Keyphrases
- question answering
- information extraction
- information retrieval
- question classification
- natural language
- natural language processing
- named entities
- visual features
- syntactic information
- low level
- relation extraction
- qa clef
- natural language questions
- question answering systems
- visual information
- multi modal
- passage retrieval
- cross language
- textual entailment recognition
- sentence retrieval
- open domain question answering
- answer extraction
- candidate answers
- qa systems
- semantic roles
- search engine