Визуальные вопросы и ответы по документам
task
ID: documentvisualquestionanswering
Related Papers
StructuralLM: Structural Pre-training for Form Understanding
AbstractLarge pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, they almost exclusively focus on text-only representation, while neglecting cell-level layout information that is important for …...
DuReadervis: A Chinese Dataset for Open-domain Document Visual Question Answering
AbstractOpen-domain question answering has been used in a wide range of applications, such as web search and enterprise search, which usually takes clean texts extracted from various formats of documents …...