PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering.
Yihao DingKaixuan RenJiabin HuangSiwen LuoSoyeon Caren HanPublished in: CoRR (2024)
Keyphrases
- question answering
- information retrieval
- information extraction
- passage retrieval
- natural language
- question classification
- natural language processing
- qa clef
- cross language
- question answering systems
- named entities
- syntactic information
- open domain question answering
- audio visual
- learning to rank
- test collection
- visual features
- information retrieval systems
- text mining
- machine translation
- retrieval systems
- multi modal
- semantic roles
- language model
- qa systems
- search engine
- answer validation
- artificial intelligence