[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-343767-105":59,"doc-detail-343767-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","flexible-web-document-analysis-for-delivery-to-narrow-bandwidth-devices","Flexible Web Document Analysis for Delivery to Narrow-Bandwidth Devices","","Flexible Web Document Analysis for Delivery to Narrow-Bandwidth Devices proposes baseline heuristics for detecting genuinely tabular information and news links within HTML pages. The work includes a prototype system applying these heuristics to deliver content from news providers’ homepages to narrow-bandwidth devices such as portable digital assistants and cellular phone displays. Evaluation is presented on 75 websites, followed by discussion of directions for future research, including replacing portal-based delivery with more functional, topic-aware filtering and content reformatting.",{"@graph":69,"@context":122},[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/flexible-web-document-analysis-for-delivery-to-narrow-bandwidth-devices/343767/",{"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/flexible-web-document-analysis-for-delivery-to-narrow-bandwidth-devices/343767.png","ImageObject",300,407,{"name":92,"@type":93},"Levi","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-11","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":19},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the document address?","Question",{"text":112,"@type":113},"It addresses how to deliver relevant web content—especially news— from HTML pages to narrow-bandwidth devices that require much smaller, reformatted summaries.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What heuristics are proposed in the paper?",{"text":117,"@type":113},"The paper proposes two baseline heuristic types: one to identify genuinely tabular content despite layout misuse of tables, and another to find self-explanatory hyperlinks to news stories.",{"name":119,"@type":110,"acceptedAnswer":120},"How is the prototype evaluated and what is discussed next?",{"text":121,"@type":113},"The prototype is evaluated on 75 websites, and the document discusses topics and directions for future research.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},343767,1791549681,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":29,"category_name":30,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":19,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":24,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144},7971461740909,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Flexible Web Document Analysis for Delivery to Narrow-Bandwidth Devices  \nGerald Penn Jianying Hu  Hengbin Luo  Ryan McDonald  \n[gpenn@cs.toronto.edu](gpenn@cs.toronto.edu) [jianhu@avaya.com](jianhu@avaya.com) [hengbinluo@hotmail.com](hengbinluo@hotmail.com) [r.mcdonald@toronto.edu](r.mcdonald@toronto.edu)  \nLucent Bell Labs University of Toronto Avaya Laboratories Language Modeling Research Dept. of Computer Science Multimedia Technologies Research  \n600 Mountain Ave . 10 King's College Rd. 211 Mt. Airy Road Murray Hill, NJ 07974, USA Toronto M5S 3G4, Canada Basking Ridge, NJ 07920, USA  \nAbstract  \nWe propose a set of baseline heuristics for identifying genuinely tabular information and news links in HTML documents. A prototype implementation of these heuristics is described for delivering content from news providers' homepages to a narrow-bandwidth device such as a portable digital assistant or cellular phone display. Its evaluation on 75 web-sites is provided, along with a discussion of topics for future research.  \n1 . Motivation  \nDelivery of content from the World Wide Web to devices other than computers with standard-sized displays is typically achieved through the use of a portal. The portal's function is to collect and prepare the content for delivery to the particular device with a great deal of attention to one of its particular modes of presentation. Ultimately, the range and potential sources of content are restricted by the portal to make this provision feasible.  \nThe present research programme was motivated by speculation that recent advances in computational linguistics and document analysis could be used to replace portals, ultimately a filter to enforce syntactic restrictions on content, with more functional restrictions gleaned from the topic or domain to which the content pertains. Given that semantic restriction, linguistic and document-based analysis of semistructured text can, in principle, be used to automatically provide the most relevant content at the right level of detail to a user and in the right format for the mode of delivery.  \nThis is very much in keeping with the original aims of markup languages such as SGML and HTML, whose containers and attributes were meant to facilitate the identification of function, salience and other semantic relations as an abstraction from how they should be used to guide layout  \nor presentation through a particular modality. The problem is that nearly all professionally designed web-sites (ab)use HTML as a means of customising the presentation of their content through a standard browser such as Netscape or Internet Explorer on a desktop or laptop computer. As a result, to the extent that their content is semantically or functionally marked at all, it is not structured well enough to be of much assistance when attempting to render it elsewhere. 1 Recent innovations in the W3C HTML standard for separating content from presentation, such as cascading style sheets, are widely used, but not so much as to replace the various proprietary extensions of HTML that actively discourage this distinction.  \nTo test this speculation, we have chosen to focus on delivering news content through narrow-bandwidth devices (NBDs), e.g., portable digital assistants and cellular phone displays, where the means of transmission and the small dimensions of the display require a drastic reduction in the size of the content, and a reformatting of the resulting summary. Although we are concerned here with providing textual content, the requirements of this task are obviously related to those of delivering HTML news content by voice using a text-to-speech synthesiser. A number of both voicebased and text-based portals already exist for this domain, of course, but as methods improve, it will be possible to refine this domain to very specific topics of news, or expand it to include content such as personal home pages, for which there is unlikely to be sufficient commercial demand to support a portal","cbCaiaeVNoRhzEQL","https://ap.wps.com/l/cbCaiaeVNoRhzEQL","pdf",141739,"English","# Motivation\n## Replacing portal-based delivery\n## Separating content from presentation\n## Challenges with semantically marked HTML\n## Delivering news to narrow-bandwidth devices\n## Heuristics for tabular content and news links","[{\"question\":\"What problem does the document address?\",\"answer\":\"It addresses how to deliver relevant web content—especially news— from HTML pages to narrow-bandwidth devices that require much smaller, reformatted summaries.\"},{\"question\":\"What heuristics are proposed in the paper?\",\"answer\":\"The paper proposes two baseline heuristic types: one to identify genuinely tabular content despite layout misuse of tables, and another to find self-explanatory hyperlinks to news stories.\"},{\"question\":\"How is the prototype evaluated and what is discussed next?\",\"answer\":\"The prototype is evaluated on 75 websites, and the document discusses topics and directions for future research.\"}]","Flexible Web Document Analysis for Delivery to Narrow-Bandwidth Devices | PDF",1790052049,13]