让论文转Markdown更快更准，直接复用原文布局信息。
Layout-Aware Text Editing for Efficient Transformation of Academic PDFs to Markdown
- 先分析文档布局，再针对性编辑，跳过重复生成。
- 比传统方法快44.5%，保持高质量转换。
- 适合需要批量处理学术文献的科研与开发人员。
以PDF格式存储的学术文档可转换为纯文本结构化标记语言，提升可访问性并支持规模化数字图书馆工作流。标记语言便于更新和定制，使学术内容更适应多样化用途，如语言语料库构建。这类文档通常包含数学公式、图表、标题、表格及密集排版的文本。现有端到端解码器变压器模型可将文档截图转为标记语言，但效率低下：需逐词重新生成本可直接复制的密集文本，浪费大量推理步骤。为此，我们提出EditTrans，一种混合编辑-生成模型，能预先从PDF中识别待编辑文本队列再开始生成标记语言。EditTrans采用在arXiv的162,127页文档上微调的轻量级分类器，基于文档布局分析模型。评估显示，相比端到端解码器变压器模型，EditTrans最高降低44.5%转换延迟，同时保持转换质量。代码与可复现的数据集生成脚本已开源。
原文摘要 · Abstract (English)
Academic documents stored in PDF format can be transformed into plain text structured markup languages to enhance accessibility and enable scalable digital library workflows. Markup languages allow for easier updates and customization, making academic content more adaptable and accessible to diverse usage, such as linguistic corpus compilation. Such documents, typically delivered in PDF format, contain complex elements including mathematical formulas, figures, headers, and tables, as well as densely layouted text. Existing end-to-end decoder transformer models can transform screenshots of documents into markup language. However, these models exhibit significant inefficiencies; their token-by-token decoding from scratch wastes a lot of inference steps in regenerating dense text that could be directly copied from PDF files. To solve this problem, we introduce EditTrans, a hybrid editing-generation model whose features allow identifying a queue of to-be-edited text from a PDF before starting to generate markup language. EditTrans contains a lightweight classifier fine-tuned from a Document Layout Analysis model on 162,127 pages of documents from arXiv. In our evaluations, EditTrans reduced the transformation latency up to 44.5% compared to end-to-end decoder transformer models, while maintaining transformation quality. Our code and reproducible dataset production scripts are open-sourced.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。