Is GPT-3 All You Need for Visual Question Answering in Cultural Heritage?
Pietro BonginiFederico BecattiniAlberto Del BimboPublished in: ECCV Workshops (1) (2022)
Keyphrases
- question answering
- cultural heritage
- digital libraries
- natural language processing
- multimedia
- passage retrieval
- information extraction
- information retrieval
- natural language
- named entities
- question classification
- cross language
- qa clef
- natural language questions
- syntactic information
- digital archives
- open domain question answering
- question answering systems
- low level
- visual features
- visual information
- sentence retrieval
- candidate answers
- answering questions
- relation extraction
- multi modal
- question answer pairs
- knowledge base