VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning.
Kang ChenXiangqian WuPublished in: CoRR (2023)
Keyphrases
- cross media
- question answering
- cross language
- named entities
- information retrieval
- knowledge base
- multimedia
- information extraction
- natural language processing
- syntactic information
- visual features
- visual information
- natural language
- relation extraction
- low level
- text retrieval
- digital content
- image retrieval
- digital libraries
- artificial intelligence
- document collections
- text documents
- text mining
- information access
- high level
- metadata