Modality-Aware Integration with Large Language Models for Knowledge-Based Visual Question Answering.
Junnan DongQinggang ZhangHuachi ZhouDaochen ZhaPai ZhengXiao HuangPublished in: ACL (1) (2024)
Keyphrases
- question answering
- language model
- passage retrieval
- information retrieval
- language modeling
- document retrieval
- probabilistic model
- sentence retrieval
- n gram
- speech recognition
- retrieval model
- information extraction
- natural language
- multi modal
- natural language processing
- cross language
- visual information
- test collection
- visual features
- query expansion
- question classification
- named entities
- question answering systems
- vector space model
- low level
- query terms
- vector space
- cross lingual
- text mining
- search engine