DocPrompt: Large-scale continue pretrain for zero-shot and few-shot document question answering
This work addresses document question answering for applications requiring efficient delivery and cost reduction, though it appears incremental.
The authors tackled document question answering by developing DocPrompt, which achieved state-of-the-art performance on four tasks, reducing annotation and labor costs in customer projects.
In this paper, we propose Docprompt for document question answering tasks with powerful zero-shot and few-shot performance. We proposed a novel weakly supervised data generation method, a novel multl-stage training method and a novel understanding model \& generation model ensemble method. We achieved state-of-the-art performance on 4 document question answering tasks. This method greatly improves the delivery efficiency and model performance of document question answering customer projects, reducing annotation costs and labor costs. Our demo can be found at https://huggingface.co/spaces/PaddlePaddle/ERNIE-Layout.