LGAINov 30, 2021

OCR-free Document Understanding Transformer

arXiv:2111.15664v5495 citationsHas Code
Originality Incremental advance
AI Analysis

This addresses inefficiencies and errors in document processing for applications like invoice analysis, though it is incremental as it builds on existing transformer architectures.

The paper tackles the problem of document understanding by proposing Donut, an OCR-free transformer model that eliminates the need for separate OCR engines, achieving state-of-the-art performance in speed and accuracy on various tasks.

Understanding document images (e.g., invoices) is a core but challenging task since it requires complex functions such as reading text and a holistic understanding of the document. Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs. Although such OCR-based approaches have shown promising performance, they suffer from 1) high computational costs for using OCR; 2) inflexibility of OCR models on languages or types of document; 3) OCR error propagation to the subsequent process. To address these issues, in this paper, we introduce a novel OCR-free VDU model named Donut, which stands for Document understanding transformer. As the first step in OCR-free VDU research, we propose a simple architecture (i.e., Transformer) with a pre-training objective (i.e., cross-entropy loss). Donut is conceptually simple yet effective. Through extensive experiments and analyses, we show a simple OCR-free VDU model, Donut, achieves state-of-the-art performances on various VDU tasks in terms of both speed and accuracy. In addition, we offer a synthetic data generator that helps the model pre-training to be flexible in various languages and domains. The code, trained model and synthetic data are available at https://github.com/clovaai/donut.

Code Implementations5 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes