MMHQA-ICL: Multimodal In-context Learning for Hybrid Question Answering over Text, Tables and Images.
Weihao LiuFangyu LeiTongxu LuoJiahe LeiShizhu HeJun ZhaoKang LiuPublished in: CoRR (2023)
Keyphrases
- question answering
- information retrieval
- text summarization
- natural language processing
- text mining
- database
- image classification
- named entities
- question classification
- information extraction
- textual entailment recognition
- natural language
- expert systems
- multi modal
- quantitative evaluation
- syntactic information
- sentence retrieval
- natural language questions