CFRet-DVQA: Coarse-to-Fine Retrieval and Efficient Tuning for Document Visual Question Answering.
Jinxu ZhangYongqi YuYu ZhangPublished in: CoRR (2024)
Keyphrases
- question answering
- coarse to fine
- passage retrieval
- information retrieval
- document retrieval
- information retrieval systems
- multiscale
- retrieval systems
- question classification
- sentence retrieval
- question answering systems
- information extraction
- multiresolution
- qa clef
- image registration
- cross language
- retrieval model
- answer extraction
- audio visual
- object detection
- natural language processing
- query expansion
- data retrieval
- named entities
- visual information
- natural language
- semantic roles
- natural language questions
- relevance model
- speech transcripts
- image database
- probabilistic model
- candidate answers
- language model
- test collection
- wordnet
- pairwise
- document collections
- image retrieval
- machine learning