RVT-Transformer: Residual Attention in Answerability Prediction on Visual Question Answering for Blind People.
Duy-Minh Nguyen-TranTung LeKhoa PhoMinh Le NguyenHuy Tien NguyenPublished in: ICCCI (CCIS Volume) (2022)
Keyphrases
- question answering
- natural language processing
- information retrieval
- passage retrieval
- cross language
- question classification
- question answering systems
- named entities
- qa clef
- low level
- information extraction
- natural language
- syntactic information
- answer validation
- natural language questions
- candidate answers
- machine learning
- relation extraction
- multi modal
- sentence retrieval
- answering questions
- visual information
- textual entailment recognition
- open domain question answering