{"id":"https://openalex.org/W2076665947","doi":"https://doi.org/10.1145/2020408.2020525","title":"Article clipper","display_name":"Article clipper","publication_year":2011,"publication_date":"2011-08-21","ids":{"openalex":"https://openalex.org/W2076665947","doi":"https://doi.org/10.1145/2020408.2020525","mag":"2076665947"},"language":"en","primary_location":{"id":"doi:10.1145/2020408.2020525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077871435","display_name":"Jian Fan","orcid":"https://orcid.org/0000-0001-5009-9588"},"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":"Jian Fan","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752685","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-6645-4721"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["Hewlett-Packard Labs, Beijing, China","Hewlett Packard Labs, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Hewlett Packard Labs, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110189276","display_name":"Suk Hwan Lim","orcid":null},"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":"Suk Hwan Lim","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","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 Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109204680","display_name":"Parag Joshi","orcid":null},"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":"Parag Joshi","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107840655","display_name":"Jerry Liu","orcid":null},"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":"Jerry Liu","raw_affiliation_strings":["Hewlett-Packard Labs, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"7879","issue":null,"first_page":"743","last_page":"746"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.97079998254776,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9697999954223633,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8476359844207764},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7211793661117554},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6355235576629639},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5033273100852966},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.4769250750541687},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.44318312406539917},{"id":"https://openalex.org/keywords/clipper","display_name":"Clipper (electronics)","score":0.4367412328720093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26881957054138184}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8476359844207764},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7211793661117554},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6355235576629639},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5033273100852966},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.4769250750541687},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.44318312406539917},{"id":"https://openalex.org/C161543725","wikidata":"https://www.wikidata.org/wiki/Q5134364","display_name":"Clipper (electronics)","level":2,"score":0.4367412328720093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26881957054138184},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2020408.2020525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020408.2020525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1976330963","https://openalex.org/W1985457184","https://openalex.org/W1991565788","https://openalex.org/W2051141368","https://openalex.org/W2140208587","https://openalex.org/W2145076056"],"related_works":["https://openalex.org/W574729402","https://openalex.org/W2431757721","https://openalex.org/W2989913170","https://openalex.org/W2000527925","https://openalex.org/W2390202966","https://openalex.org/W4385333561","https://openalex.org/W2990460803","https://openalex.org/W2000745862","https://openalex.org/W36911888","https://openalex.org/W4385731361"],"abstract_inverted_index":{"Many":[0],"people":[1],"use":[2,131],"the":[3,6,45,66,69,78,82,102,109,116,124],"Web":[4],"as":[5,23,90],"main":[7],"source":[8],"of":[9,85,101,167,182],"information":[10,98],"in":[11,104],"their":[12],"daily":[13],"lives.":[14],"However,":[15],"most":[16],"web":[17,52,184,189],"pages":[18,185],"contain":[19],"non-informative":[20],"components":[21,88],"such":[22,89,196],"side":[24],"bars,":[25],"footers,":[26],"headers,":[27],"and":[28,50,94,129,137,146,151,160],"advertisements,":[29],"which":[30],"are":[31,61],"undesirable":[32],"for":[33,127,133],"certain":[34],"applications":[35],"like":[36],"printing.":[37],"We":[38,191],"demonstrate":[39],"a":[40,105,175,197],"system":[41,74,114,169],"that":[42,60],"automatically":[43],"extracts":[44],"informative":[46],"contents":[47],"from":[48,186],"news-":[49],"blog-like":[51],"pages.":[53],"In":[54],"contrast":[55],"to":[56,63,122,130],"many":[57],"existing":[58],"methods":[59],"limited":[62],"identifying":[64],"only":[65,76],"text":[67,111],"or":[68],"bounding":[70],"rectangular":[71],"region,":[72],"our":[73,113,168],"not":[75],"identifies":[77],"content":[79,87,103],"but":[80],"also":[81],"structural":[83,97],"roles":[84],"various":[86],"title,":[91],"paragraphs,":[92],"images":[93],"captions.":[95],"The":[96,165],"enables":[99],"re-layout":[100],"pleasing":[106],"way.":[107],"Besides":[108],"article":[110],"extraction,":[112],"includes":[115],"following":[117],"components:":[118],"1)":[119],"print-link":[120],"detection":[121,141,153],"identify":[123],"URL":[125,163],"link":[126],"printing,":[128],"it":[132],"more":[134],"reliable":[135],"analysis":[136],"recognition;":[138],"2)":[139],"title":[140],"incorporating":[142],"both":[143],"visual":[144,156],"cues":[145],"HTML":[147],"tags;":[148],"3)":[149],"image":[150],"caption":[152],"utilizing":[154],"extensive":[155],"cues;":[157],"4)":[158],"multiple-page":[159],"next":[161],"page":[162],"detection.":[164],"performance":[166],"has":[170],"been":[171],"thoroughly":[172],"evaluated":[173],"using":[174,195],"human":[176],"labeled":[177],"ground":[178],"truth":[179],"dataset":[180],"consisting":[181],"2000":[183],"100":[187],"major":[188],"sites.":[190],"show":[192],"accurate":[193],"results":[194],"dataset.":[198]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}