@inproceedings{766b0dfc01514f1ba8fcbf9730668e92,
title = "DocBank: A Benchmark Dataset for Document Layout Analysis",
abstract = "Document layout analysis usually relies on computer vision models to understand documents while ignoring textual information that is vital to capture. Meanwhile, high quality labeled datasets with both visual and textual information are still insufficient. In this paper, we present DocBank, a benchmark dataset that contains 500K document pages with fine-grained token-level annotations for document layout analysis. DocBank is constructed using a simple yet effective way with weak supervision from the LATEX documents available on the arXiv.com. With DocBank, models from different modalities can be compared fairly and multi-modal approaches will be further investigated and boost the performance of document layout analysis. We build several strong baselines and manually split train/dev/test sets for evaluation. Experiment results show that models trained on DocBank accurately recognize the layout information for a variety of documents. The DocBank dataset is publicly available at https://github.com/doc-analysis/DocBank.",
author = "Minghao Li and Yiheng Xu and Lei Cui and Shaohan Huang and Furu Wei and Zhoujun Li and Ming Zhou",
note = "Publisher Copyright: {\textcopyright} 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.; 28th International Conference on Computational Linguistics, COLING 2020 ; Conference date: 08-12-2020 Through 13-12-2020",
year = "2020",
language = "英语",
series = "COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "949--960",
editor = "Donia Scott and Nuria Bel and Chengqing Zong",
booktitle = "COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference",
address = "澳大利亚",
}