MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model.
Le ZhangYihong WuFengran MoJian-Yun NieAishwarya AgrawalPublished in: CoRR (2023)
Keyphrases
- multi modal
- language model
- open domain question answering
- language modeling
- question answering
- probabilistic model
- document retrieval
- retrieval model
- information retrieval
- n gram
- speech recognition
- audio visual
- query expansion
- test collection
- high dimensional
- image annotation
- passage retrieval
- smoothing methods
- mixture model
- query terms
- machine learning
- cross language
- image classification
- pseudo relevance feedback
- video search
- translation model
- answer extraction