{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/layoutreader-pre-training-of-text-and-layout","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","arxiv_id":"2108.11591","date":"2021-08-26","proceeding":"EMNLP 2021 11","authors":["Zilong Wang","Yiheng Xu","Lei Cui","Jingbo Shang","Furu Wei"],"abstract":"Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large enough dataset. We observe that the reading order of WORD documents is embedded in their XML metadata; meanwhile, it is easy to convert WORD documents to PDFs or images. Therefore, in an automated manner, we construct ReadingBank, a benchmark dataset that contains reading order, text, and layout information for 500,000 document images covering a wide spectrum of document types. This first-ever large-scale dataset unleashes the power of deep neural networks for reading order detection. Specifically, our proposed LayoutReader captures the text and layout information for reading order prediction using the seq2seq model. It performs almost perfectly in reading order detection and significantly improves both open-source and commercial OCR engines in ordering text lines in their results in our experiments. We will release the dataset and model at \\url{https://aka.ms/layoutreader}.","url_abs":"https://arxiv.org/abs/2108.11591v2","url_pdf":"https://arxiv.org/pdf/2108.11591v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"layoutreader-pre-training-of-text-and-layout","repo_url":"https://github.com/microsoft/unilm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"document-layout-analysis","task_name":"Document Layout Analysis"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"reading-order-detection","task_name":"Reading Order Detection"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"layoutreader","method_name":"LayoutReader"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[{"slug":"readingbank","name":"ReadingBank","full_name":""}],"methods_introduced":[{"slug":"layoutreader","name":"LayoutReader","full_name":"LayoutReader"}],"results":[{"leaderboard":"/sota/reading-order-detection-on-roor","task":"Reading Order Detection","dataset":"ROOR","model":"LayoutReader","rank_in_archive_order":4,"of":4,"metrics":{"Segment-level F1":"9.44"},"uses_additional_data":false},{"leaderboard":"/sota/reading-order-detection-on-readingbank","task":"Reading Order Detection","dataset":"ReadingBank","model":"LayoutReader","rank_in_archive_order":2,"of":2,"metrics":{"Average Page-level BLEU":"98.19","Average Relative Distance (ARD)":"1.75"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.11591","atlas_url":"https://app.syntology.ai/?focus=2108.11591","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}