MM-PhyQA: Multimodal Physics Question-Answering with Multi-image CoT Prompting.
Avinash AnandJanak KapuriyaApoorv SinghJay SarafNaman LalAstha VermaRushali GuptaRajiv Ratn ShahPublished in: PAKDD (5) (2024)
Keyphrases
- question answering
- image features
- image retrieval
- image content
- information extraction
- named entities
- natural language
- syntactic information
- image classification
- natural language processing
- low level
- information retrieval
- question classification
- open domain question answering
- image representation
- cross language
- natural language questions
- relation extraction
- passage retrieval
- question answering systems
- qa clef
- answering questions