{"id":"https://openalex.org/W2030908643","doi":"https://doi.org/10.1145/2034691.2034721","title":"A versatile model for web page representation, information extraction and content re-packaging","display_name":"A versatile model for web page representation, information extraction and content re-packaging","publication_year":2011,"publication_date":"2011-09-19","ids":{"openalex":"https://openalex.org/W2030908643","doi":"https://doi.org/10.1145/2034691.2034721","mag":"2030908643"},"language":"en","primary_location":{"id":"doi:10.1145/2034691.2034721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2034691.2034721","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/A5002485657","display_name":"Bernhard Kr\u00fcpl-Sypien","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Bernhard Kr\u00fcpl-Sypien","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008812580","display_name":"Ruslan R. Fayzrakhmanov","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ruslan R. Fayzrakhmanov","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046672766","display_name":"Wolfgang Holzinger","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Wolfgang Holzinger","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087200426","display_name":"Mathias Panzenb\u00f6ck","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Mathias Panzenb\u00f6ck","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055923468","display_name":"Robert Baumgartner","orcid":"https://orcid.org/0000-0003-0899-4903"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Robert Baumgartner","raw_affiliation_strings":["TU Wien, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":3.0571,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92675006,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7974996566772461},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5924543142318726},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4880582094192505},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.47957557439804077},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4685780704021454},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4562188386917114},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41154661774635315},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3726200461387634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7974996566772461},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5924543142318726},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4880582094192505},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.47957557439804077},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4685780704021454},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4562188386917114},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41154661774635315},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3726200461387634},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2034691.2034721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2034691.2034721","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.395.4307","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.395.4307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dbai.tuwien.ac.at/staff/fayzrakh/proceedings/Krupl-Sypien2011DocEng.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W150957605","https://openalex.org/W1517957937","https://openalex.org/W1963959122","https://openalex.org/W2017537431","https://openalex.org/W2017835788","https://openalex.org/W2036114781","https://openalex.org/W2067161274","https://openalex.org/W2082413760","https://openalex.org/W2090193136","https://openalex.org/W2096031153","https://openalex.org/W2102189859","https://openalex.org/W2123235395","https://openalex.org/W2136282242","https://openalex.org/W3019546484","https://openalex.org/W3165850736"],"related_works":["https://openalex.org/W2411679502","https://openalex.org/W1788528807","https://openalex.org/W1975174578","https://openalex.org/W104581431","https://openalex.org/W2725657302","https://openalex.org/W240673130","https://openalex.org/W1548492051","https://openalex.org/W1545545132","https://openalex.org/W2800975405","https://openalex.org/W1512524377"],"abstract_inverted_index":{"On":[0],"today's":[1],"Web,":[2],"designers":[3],"take":[4],"huge":[5],"efforts":[6],"to":[7,35,48,60,77],"create":[8],"visually":[9],"rich":[10],"websites":[11],"that":[12,91,169],"boast":[13],"a":[14,45,67,104,111,120,140],"magnitude":[15],"of":[16,103,113,156,193],"interactive":[17],"elements.":[18],"Contrarily,":[19],"most":[20,63],"web":[21,50,89,105,194],"information":[22],"extraction":[23],"(WIE)":[24],"algorithms":[25],"are":[26],"still":[27],"based":[28,55],"on":[29,56,116,132,171],"attributed":[30],"tree":[31],"methods":[32],"which":[33,160],"struggle":[34],"deal":[36],"with":[37,87],"this":[38,41,133],"complexity.":[39],"In":[40],"paper,":[42],"we":[43,107,135,180,183],"introduce":[44,136],"versatile":[46],"model":[47,53,189],"represent":[49],"documents.":[51],"The":[52,152],"is":[54,85],"gestalt":[57,114,117],"theory":[58],"principles---trying":[59],"capture":[61],"the":[62,100,157,162,166,191],"important":[64],"aspects":[65],"in":[66,190],"formally":[68],"exact":[69],"way.":[70],"It":[71],"(i)":[72],"represents":[73],"and":[74,81,148,165,173,186],"unifies":[75],"access":[76],"visual":[78,101],"layout,":[79],"content":[80,150],"functional":[82],"aspects;":[83],"(ii)":[84],"implemented":[86],"semantic":[88],"techniques":[90],"can":[92],"be":[93,124],"leveraged":[94],"for":[95],"i.e.":[96],"automatic":[97],"reasoning.":[98],"Considering":[99],"appearance":[102],"page,":[106],"view":[108],"it":[109,125],"as":[110],"collection":[112],"figures---based":[115],"primitives---each":[118],"representing":[119],"specific":[121],"design":[122,144],"pattern,":[123],"navigation":[126],"menus":[127],"or":[128],"news":[129],"articles.":[130],"Based":[131],"model,":[134,159],"our":[137,188],"WIE":[138],"methodology,":[139],"re-engineering":[141],"process":[142],"involving":[143],"patterns,":[145],"statistical":[146],"distributions":[147],"text":[149],"properties.":[151],"complete":[153],"framework":[154],"consists":[155],"UOM":[158],"formalizes":[161],"mentioned":[163],"components,":[164],"MANM":[167],"layer":[168],"hints":[170],"structure":[172],"serialization,":[174],"providing":[175],"document":[176],"re-packaging":[177],"foundations.":[178],"Finally,":[179],"discuss":[181],"how":[182],"have":[184],"applied":[185],"evaluated":[187],"area":[192],"accessibility.":[195]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
