SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images.
Ryota TanakaKyosuke NishidaKosuke NishidaTaku HasegawaItsumi SaitoKuniko SaitoPublished in: AAAI (2023)
Keyphrases
- question answering
- multiple images
- passage retrieval
- information retrieval
- single image
- multiple views
- text summarization
- information extraction
- natural language processing
- visual information
- light source
- natural language
- candidate answers
- question classification
- document collections
- syntactic information
- retrieval systems
- qa clef
- sentence retrieval
- document retrieval
- information retrieval systems
- natural language questions
- document classification
- cross language
- text documents
- named entities
- keywords
- visual features
- language model
- machine learning
- answering questions
- viewpoint
- qa systems
- vector space model
- semantic roles
- retrieval model
- answer validation