Multimodal Reranking for Knowledge-Intensive Visual Question Answering.
Haoyang WenHonglei ZhuangHamed ZamaniAlexander HauptmannMichael BenderskyPublished in: CoRR (2024)
Keyphrases
- question answering
- knowledge intensive
- knowledge acquisition
- visual features
- information extraction
- passage retrieval
- natural language processing
- question classification
- named entities
- cross language
- syntactic information
- visual information
- knowledge management
- question answering systems
- information retrieval
- video search
- human resources
- image search
- answer validation
- natural language
- multi modal
- software development
- image classification
- law enforcement
- qa clef
- databases
- natural language questions
- answer extraction
- machine learning
- candidate answers
- knowledge base
- case study
- semantic roles
- relational databases
- low level
- audio visual