[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-344992-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-344992-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","pdf2xml-converting-pdf-to-xml-paper-overview","PDF2XML - Converting PDF to XML - Paper Overview","","XML is a structured markup language built to enable easy interchange of structured documents over the Internet and integration with database systems. PDF is a page-layout format designed to reproduce the look of a page, but it does not preserve original structure such as paragraphs and tables, making PDF-to-XML conversion difficult. The work presents techniques and a system called PDF2XML that automatically converts PDFs with minimum human interaction as part of a data conversion project.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/pdf2xml-converting-pdf-to-xml-paper-overview/344992/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/pdf2xml-converting-pdf-to-xml-paper-overview/344992.png","ImageObject",300,407,{"name":42,"@type":43},"wps_ap_test_251126_0180","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-31","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is converting PDF to XML challenging?","Question",{"text":63,"@type":64},"PDF reproduces page appearance but does not include original document structure such as paragraph and table information. This absence makes automatic reconstruction difficult.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What is the main goal of the PDF2XML system?",{"text":68,"@type":64},"PDF2XML is designed to convert PDF documents into XML with minimum human interaction by automating the conversion workflow.",{"name":70,"@type":61,"acceptedAnswer":71},"Which phases does PDF2XML use to perform the conversion?",{"text":72,"@type":64},"The system proceeds through four phases: PDF Extraction, Structure Reconstruction, Manual Modification, and XML Wrapping.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},344992,1790302035,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":33,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":123,"preview_page_count":33,"preview_urls":144},8796095027276,"https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=","PDF2XML: Converting PDF to XML  \nYonggao Yang Kwang Paick Yanxiong Peng Yukong Zhang Department of Computer Science  \nPrairie View A&M University  \nPrairie View, TX 77446  \nAbstract: XML is a markup language for documents containing structured information. It is designed to make it easy to interchange structured documents over the Internet and further integrate them with management database system. PDF is a document format intended to electronically reproduce the look of a page. There is a huge demand of converting existing PDF documents into XML documents, so that they will be searchable and manageable. Since PDF is basically a page layout format and does not carry original document structure, converting PDF to XML remains a challenging task. This paper addresses the related technique problems and explores approaches. As part of the Data Conversion Project under development at the Data Conversion Center funded by DoD, we present a system, PDF2XML, designed to automatically perform the conversion with minimum human interaction.  \nKeywords: Data Conversion, PDF, XML  \n1. Introduction  \nPortable Document Format, PDF, is a widely used electronic document format intended to electronically reproduce the look of a page [1, 2] . It was designed to be a publishing format, which is often referred to as “Electronic Paper”. However, a PDF document does not contain any structure information that its original electronic file possesses, such as paragraph information, table structures, and so forth. This allows a PDF document to be usually much smaller in size than its original electronic file in other formats, thus makes PDF documents convenient for transmitting on the Internet.  \nEXtensible Markup Language, XML, is a markup language for documents containing structured information [3, 4, 5] . It allows that richly structured documents can represent database data as well as other kinds of structured data, and be used over the web in communication between business applications. XML provides a facility to define tags and the structural relationships between them.  \nHuge amount of documents are generated everyday and stored in PDF format. Furthermore, we have very large amount of legacy PDF documents without their original electronic files from which they were generated. Virk [8] lists the gains we can achieve by converting other documents into XML format. It might be easy to perform some conversions among various formats, such as XML to PDF and HTML to XML [6, 7] .  \nCurrently most of the conversion work is done manually, thus is time-consuming and error-prone. Few efforts are directed towards designing automatic conversion tools. Ouahid and Karmouch [6] address methods of converting web pages into XML documents. Youn and Ku [7] discuss issues of migrating data from one system to another, without mentioning PDF-to-XML. One commercial software worth of mention is Omnimark [9], which is designed to help convert documents in RTF format into XML format.  \nWe are aware of that it is extremely difficult to develop a system to automatically conduct the 100% of PDF to XML conversion due to the versatility of PDF documents and XML DTD specification. We lunched a project to develop a computer system capable of performing the 60~70% of  \nthe conversion task automatically, thus leaving about 30% of conversion task to be done manually. Asthe result of this project, a system, PDF2XML, was developed.  \n2. Convert PDF to XML  \nOur goal is to design and implement a system to help convert PDF document into XML documents with minimum human interaction. The structure of the system, PDF2XML, is depicted in Figure 1. The filled thick arrows show the flow of the data from the input of the PDF document to the output of the XML document. It goes through four phases: (1) PDF Extraction; (2) Structure Reconstruction; (3) Manual Modification; and (4) XML Wrapping.  \n2  \nOriginal Document Structure  Reconstructor   \n|  |  3\u003Cbr>Manual  Modification \u003Cbr>\u003Cbr>|\n| --- | --- |\n","cbCaiaz4Wo0vYorn","https://ap.wps.com/l/cbCaiaz4Wo0vYorn","pdf",322435,"English","# Introduction\n## Background: PDF as page layout\n## XML for structured documents\n## Need for automatic conversion\n# Convert PDF to XML\n## Phase-I: Information extraction from PDF\n## Phase-II: Reconstruction of original document structure\n## Paragraph merger","[{\"question\":\"Why is converting PDF to XML challenging?\",\"answer\":\"PDF reproduces page appearance but does not include original document structure such as paragraph and table information. This absence makes automatic reconstruction difficult.\"},{\"question\":\"What is the main goal of the PDF2XML system?\",\"answer\":\"PDF2XML is designed to convert PDF documents into XML with minimum human interaction by automating the conversion workflow.\"},{\"question\":\"Which phases does PDF2XML use to perform the conversion?\",\"answer\":\"The system proceeds through four phases: PDF Extraction, Structure Reconstruction, Manual Modification, and XML Wrapping.\"}]","PDF2XML - Converting PDF to XML - Paper Overview | PDF",1790056119,[145,149,153,157],{"page_no":22,"url":146,"width":147,"height":148},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/44eada19ce94bec7f6cd97393827b213.webp",983,1272,{"page_no":26,"url":150,"width":151,"height":152},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/4cab23a4edb75af17dc2502b7d3ad3c7.webp",982,1270,{"page_no":30,"url":154,"width":155,"height":156},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0a827c7f8c515c8c13c36b090f6c1674.webp",981,1269,{"page_no":33,"url":158,"width":159,"height":160},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e73e03236f42c79a9db12bca7e8a44dd.webp",980,1268]