ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in Images.
Huy Quang PhamThang Kien-Bao NguyenQuan Van NguyenDan Quang TranNghia Hieu NguyenKiet Van NguyenNgan Luu-Thuy NguyenPublished in: CoRR (2024)
Keyphrases
- question answering
- benchmark datasets
- information retrieval
- natural language processing
- syntactic information
- information extraction
- natural language
- cross language
- visual data
- text mining
- question classification
- passage retrieval
- natural language questions
- named entities
- named entity recognition
- image classification
- text summarization
- qa clef
- answering questions
- textual entailment recognition
- relation extraction