ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding.
Bingning WangFeiyang LvTing YaoJin MaYu LuoHaijin LiangPublished in: CIKM (2022)
Keyphrases
- multi modal
- question answering
- real world
- natural language
- passage retrieval
- question classification
- information extraction
- question answering systems
- natural language processing
- named entities
- audio visual
- syntactic information
- information retrieval
- multi modality
- answering questions
- qa clef
- cross language
- high dimensional
- data mining
- semantic roles
- artificial intelligence
- natural language questions
- answer extraction
- qa systems
- image annotation
- test collection
- feature set
- machine learning