LayoutLM: Pre-training of Text and Layout for Document Image Understanding

Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the wide spread of pre-training models for NLP applications, they almost focused on text-level manipulation, while neglecting the layout and style information that is vital for document image understanding. In this paper, we propose \textbf{LayoutLM} to jointly model the interaction between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding tasks such as information extraction from scanned documents. We also leverage the image features to incorporate the style information of words in LayoutLM. To the best of our knowledge, this is the first time that text and layout are jointly learned in a single framework for document-level pre-training, leading to significant performance improvement in downstream tasks for document image understanding.