[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-656104-105":59,"doc-detail-656104-en":122},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":115,"head_meta":117,"extra_data":119,"updated_unix":121},105,"en","diagramflyer-a-search-engine-for-data-driven-diagrams","DiagramFlyer - A Search Engine for Data-Driven Diagrams","","A large amount of data becomes discoverable only when converted into data-driven diagrams such as bar charts and scatterplots, yet current text and image search engines largely ignore diagram-specific structure. DiagramFlyer recovers semantic roles of diagram components (axes, labels, and related elements) to support faceted indexing and retrieval for statistical charts. It expands queries to retrieve not only exact matches but also diagrams likely related through their production pipelines, demonstrating performance on 300k+ images from 150k+ PDFs.",{"@graph":69,"@context":114},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":30,"@type":76,"position":81},"https://docshare.wps.com/document/technology/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/diagramflyer-a-search-engine-for-data-driven-diagrams/656104/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/diagramflyer-a-search-engine-for-data-driven-diagrams/656104.png","ImageObject",300,407,{"name":92,"@type":93},"Dewi_Sukmawati","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-02","2026-10-25",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108],{"name":109,"@type":110,"acceptedAnswer":111},"What is DiagramFlyer’s unique query capability?","Question",{"text":112,"@type":113},"It expands queries to include diagrams that are likely related through their production pipelines, not just exactly matching diagrams.","Answer","https://schema.org",{"og:url":83,"og:type":116,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":118,"canonical":83},"index,follow",{"doc_id":120,"site_id":62},656104,1792966438,{"code":4,"msg":5,"data":123},{"doc_id":120,"user_id":124,"nickname":92,"user_avatar":125,"doc_module":4,"category_id":29,"category_name":30,"doc_title":65,"doc_description":67,"doc_content":126,"file_id":127,"file_url":128,"file_type":129,"file_size":130,"view_count":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":19,"language":131,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":132,"faqs":133,"seo_title":134,"seo_description":67,"update_tm":121,"read_time":52},962094243415,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","DiagramFlyer: A Search Engine for Data-Driven Diagrams  \nZhe Chen  \nUniversity of Michigan Ann Arbor, MI 48109-2121  \n[chenzhe@umich.edu](chenzhe@umich.edu)  \nMichael Cafarella  \nUniversity of Michigan Ann Arbor, MI 48109-2121  \n[michjc@umich.edu](michjc@umich.edu)  \nEytan Adar  \nUniversity of Michigan Ann Arbor, MI 48109-2121  \n[eadar@umich.edu](eadar@umich.edu)  \nABSTRACT  \nA large amount of data is available only through data-driven diagrams such as bar charts and scatterplots. These diagrams are stylized mixtures of graphics and text and are the result of complicated data-centric production pipelines. Unfortunately, neither text nor image search engines exploit these diagram-speci􀀌c properties, making it di􀀎cult for users to 􀀌nd relevant diagrams in a large corpus. In response, we propose DiagramFlyer, a search engine for 􀀌nding data-driven diagrams on the web. By recovering the semantic roles of diagram components (e.g. , axes, labels, etc.), we provide faceted indexing and retrieval for various statistical diagrams. A unique feature of DiagramFlyer is that it is able to \\expand\" queries to include not only exactly matching diagrams, but also diagrams that are likely to be related in terms of their production pipelines. We demonstrate the resulting search system by indexing over 300k images pulled from over 150k PDF documents.  \nCategories and Subject Descriptors  \nH.4.0 [Information Systems]: Information systems applications|General  \nKeywords  \nWeb search; diagrams; information extraction  \n1. INTRODUCTION  \nData-driven diagrams (or statistical graphics) are an important method for communicating complex information. Diagrams, a stylized mixture of graphics and text, o􀀋er succinct quantitative summaries of data that motivate the overall document's content. Indeed, for many technical documents, the diagrams may be readers' only access to the raw data underlying the documents' conclusions. Especially for quantitative disciplines such as 􀀌nance, public policy, and the sciences, certain diagrams could be even more valuable than the surrounding text.  \nCopyright is held by the International World Wide Web Conference Committee (IW3C2) . IW3C2 reserves the right to provide a hyperlink to the author's site if the Material is used in electronic media.  \nWWW 2015 Companion, May 18–22, 2015, Florence, Italy. ACM 978-1-4503-3473-0/15/05 .  \n[http://dx.doi.org/10.1145/2740908.2742831](http://dx.doi.org/10.1145/2740908.2742831) .  \nConsider a chemist who wants to 􀀌nd all published experiments about a class of compounds called metal-organic frameworks [10] . Such materials are promising candidates for a range of applications, including carbon dioxide absorption and hydrogen storage. A common experiment for these materials is to examine the relationship between temperature and, say, H2 uptake. Unfortunately there is no reliable shared database of experimental results on this topic: the most authoritative source of data on this topic is theset of relevant diagrams published in scienti􀀌c papers. The chemist may be uninterested in the scienti􀀌c paper text: the compelling information is embedded in the diagram alone. It is easy to imagine similar diagram-driven information needs for demographers, public health experts, and other quantitative professionals. It would thus be useful to be able to search for diagrams per se, not just relevant documents.  \nBeyond domain experts, the ability to 􀀌nd similar (or alternative) diagrams may even be highly useful for average citizens. There is an increasing amount of information given to the public through visualizations. In some situations, this presentation can be highly misleading. For example, the original \\Obamacare Enrollment\" diagram from Fox News displayed a \\false baseline\" (see Figure 1(a)) . Here, we maybe interested in identifying corrected versions of the diagram (Figure 1(b)) or alternative representations (Figure 1(c)) . Finding these diagrams automatically can correct misconceptions and","cbCaigopcsuuFFZT","https://ap.wps.com/l/cbCaigopcsuuFFZT","pdf",2999739,"English","# Introduction\n## Motivation: why diagram-only search matters\n## Related work: text, image, and commercial diagram retrieval\n## Key idea: exploiting diagram generation pipelines","[{\"question\":\"What is DiagramFlyer’s unique query capability?\",\"answer\":\"It expands queries to include diagrams that are likely related through their production pipelines, not just exactly matching diagrams.\"}]","DiagramFlyer - A Search Engine for Data-Driven Diagrams | PDF"]