PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks
This addresses the need for improved document image parsing in production and daily life, but appears incremental as it builds on existing multimodal models with training tricks.
The authors tackled the problem of fast and accurate parsing of document images by developing PP-DocBee, a multimodal large language model for end-to-end document image understanding, achieving state-of-the-art results on English benchmarks and outperforming existing models in Chinese document understanding.
With the rapid advancement of digitalization, various document images are being applied more extensively in production and daily life, and there is an increasingly urgent need for fast and accurate parsing of the content in document images. Therefore, this report presents PP-DocBee, a novel multimodal large language model designed for end-to-end document image understanding. First, we develop a data synthesis strategy tailored to document scenarios in which we build a diverse dataset to improve the model generalization. Then, we apply a few training techniques, including dynamic proportional sampling, data preprocessing, and OCR postprocessing strategies. Extensive evaluations demonstrate the superior performance of PP-DocBee, achieving state-of-the-art results on English document understanding benchmarks and even outperforming existing open source and commercial models in Chinese document understanding. The source code and pre-trained models are publicly available at \href{https://github.com/PaddlePaddle/PaddleMIX}{https://github.com/PaddlePaddle/PaddleMIX}.