FNet with Cross-Attention Encoder for Visual Question Answering.
Samar I. ZekrallahNour El-Deen KhalifaAboul Ella HassanienPublished in: AISI (2022)
Keyphrases
- question answering
- natural language processing
- information retrieval
- question classification
- visual information
- named entities
- qa clef
- natural language
- syntactic information
- information extraction
- passage retrieval
- cross language
- relation extraction
- visual features
- sentence retrieval
- natural language questions
- semantic roles
- open domain question answering
- machine learning
- question answering systems
- multi modal
- low level
- answer extraction
- keywords
- answering questions
- textual entailment recognition