MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering.
Jingqun TangQi LiuYongjie YeJinghui LuShu WeiChunhui LinWanqing LiMohamad Fitri Faiz Bin MahmoodHao FengZhen ZhaoYanjie WangYuliang LiuHao LiuXiang BaiCan HuangPublished in: CoRR (2024)
Keyphrases
- question answering
- cross language
- syntactic information
- information retrieval
- text summarization
- information extraction
- natural language
- textual entailment recognition
- qa clef
- question classification
- named entities
- natural language processing
- text retrieval
- text mining
- free text
- visual features
- passage retrieval
- cross language information retrieval
- relation extraction
- keywords
- question answering systems
- natural language questions
- question answer pairs
- semantic roles
- qa systems
- answer validation
- machine learning
- news video
- video search
- query translation
- semantic information
- visual information