{"id":"https://openalex.org/W1965994683","doi":"https://doi.org/10.1145/2034691.2034711","title":"Print-friendly page extraction for web printing service","display_name":"Print-friendly page extraction for web printing service","publication_year":2011,"publication_date":"2011-09-19","ids":{"openalex":"https://openalex.org/W1965994683","doi":"https://doi.org/10.1145/2034691.2034711","mag":"1965994683"},"language":"en","primary_location":{"id":"doi:10.1145/2034691.2034711","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2034691.2034711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039468987","display_name":"Sam Liu","orcid":"https://orcid.org/0000-0003-2364-7774"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Liu","raw_affiliation_strings":["Hewlett-Packard, Palo Alto, CA, USA","Hewlett-Packard , Palo Alto, CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]},{"raw_affiliation_string":"Hewlett-Packard , Palo Alto, CA, USA#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084502605","display_name":"Conglei Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong-Lei Yao","raw_affiliation_strings":["Hewlett-Packard, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12828718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9778000116348267,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13976","display_name":"Web visibility and informetrics","score":0.9523000121116638,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7817867994308472},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7718347311019897},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6014586687088013},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.5833208560943604},{"id":"https://openalex.org/keywords/user-friendly","display_name":"User Friendly","score":0.41607147455215454},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37285012006759644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817867994308472},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7718347311019897},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6014586687088013},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.5833208560943604},{"id":"https://openalex.org/C61437842","wikidata":"https://www.wikidata.org/wiki/Q281291","display_name":"User Friendly","level":2,"score":0.41607147455215454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37285012006759644},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2034691.2034711","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2034691.2034711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1991565788","https://openalex.org/W2087406717","https://openalex.org/W2129595335","https://openalex.org/W2140208587"],"related_works":["https://openalex.org/W2245616560","https://openalex.org/W2351804282","https://openalex.org/W2884859571","https://openalex.org/W2048998278","https://openalex.org/W1556894713","https://openalex.org/W1490416172","https://openalex.org/W158130761","https://openalex.org/W2588706232","https://openalex.org/W2096877906","https://openalex.org/W1488511360"],"abstract_inverted_index":{"Printing":[0],"Web":[1,29,52,57,84],"pages":[2,12,30,43,82,90,184],"from":[3,80,88,97],"browsers":[4],"usually":[5],"results":[6,204],"in":[7,110],"unsatisfactory":[8],"printouts":[9],"because":[10],"the":[11,45,55,98,107,124,175,183,190,195],"are":[13,103,185],"typically":[14],"ill":[15],"formatted":[16,65],"and":[17,25,78,93,216],"contain":[18,35,177],"non-informative":[19],"content":[20,58,76],"such":[21,31,145],"as":[22,32,146],"navigation":[23],"menu":[24],"ads.":[26],"Thus,":[27],"print-worthy":[28],"articles":[33],"generally":[34],"hyperlinks":[36],"(or":[37],"links)":[38],"that":[39,112,198,206],"lead":[40],"to":[41,62,141],"print-friendly":[42,81,89,143,222],"containing":[44],"salient":[46],"content.":[47],"For":[48,132],"a":[49,70,136,164,178],"more":[50,94,117],"desirable":[51],"printing":[53],"experience,":[54],"main":[56],"should":[59],"be":[60,127],"extracted":[61],"produce":[63],"well":[64],"pages.":[66],"This":[67],"paper":[68],"describes":[69],"cloud":[71],"service":[72],"based":[73],"on":[74],"automatic":[75],"extraction":[77,87],"repurposing":[79],"for":[83,221],"printing.":[85],"Content":[86],"is":[91,135,201,209],"simpler":[92],"reliable":[95],"than":[96,119],"original":[99],"pages,":[100,144],"but":[101,181],"there":[102,134],"many":[104],"variations":[105],"of":[106,138,174,211],"print-link":[108,115],"representations":[109],"HTML":[111],"make":[113],"robust":[114],"detection":[116],"difficult":[118],"it":[120],"first":[121],"appears.":[122],"First,":[123],"link":[125,223],"can":[126],"text-based,":[128],"image-based,":[129],"or":[130,162,193],"both.":[131],"example,":[133],"lexicon":[137],"phrases":[139],"used":[140],"indicate":[142],"\"print\",":[147],"\"print":[148],"article\",":[149],"\"print-friendly":[150],"version\",":[151],"etc.":[152],"In":[153],"addition,":[154],"some":[155],"links":[156,176],"use":[157],"printer-resembling":[158],"image":[159],"icons":[160],"with":[161],"without":[163],"print":[165],"phrase":[166],"present.":[167,202],"To":[168],"complicate":[169],"matter":[170],"further,":[171],"not":[172],"all":[173],"valid":[179],"URL,":[180],"instead":[182],"dynamically":[186],"generated":[187],"either":[188],"by":[189,194],"client":[191],"Javascript":[192],"server,":[196],"so":[197],"no":[199],"URL":[200],"Experimental":[203],"suggest":[205],"our":[207],"solution":[208],"capable":[210],"achieving":[212],"over":[213],"99%":[214],"precision":[215],"97%":[217],"recall":[218],"performance":[219],"measures":[220],"extraction.":[224]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
