Multimodal Inverse Cloze Task for Knowledge-Based Visual Question Answering.
Paul LernerOlivier FerretCamille GuinaudeauPublished in: ECIR (1) (2023)
Keyphrases
- question answering
- question classification
- information retrieval
- natural language
- question answering systems
- information extraction
- passage retrieval
- named entities
- natural language processing
- qa clef
- natural language questions
- cross language
- visual information
- syntactic information
- multi modal
- open domain question answering
- artificial intelligence
- relation extraction
- visual data
- low level
- answer extraction
- expert systems
- audio visual
- language modeling
- candidate answers
- relational databases
- sentence retrieval
- answering questions
- answer validation
- multimedia