{"id":"https://openalex.org/W2086017131","doi":"https://doi.org/10.1145/1141277.1141534","title":"Template detection for large scale search engines","display_name":"Template detection for large scale search engines","publication_year":2006,"publication_date":"2006-04-23","ids":{"openalex":"https://openalex.org/W2086017131","doi":"https://doi.org/10.1145/1141277.1141534","mag":"2086017131"},"language":"en","primary_location":{"id":"doi:10.1145/1141277.1141534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","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/A5035208775","display_name":"Liang Chen","orcid":"https://orcid.org/0000-0003-0579-2716"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liang Chen","raw_affiliation_strings":["Tsinghua University, Beijing, P.R.China","TsingHua University, Beijing, P.R. China#TAB#"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, P.R.China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"TsingHua University, Beijing, P.R. China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054765777","display_name":"Shaozhi Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaozhi Ye","raw_affiliation_strings":["University of California, Davis, CA","University of California, Davis, CA,#TAB#"],"affiliations":[{"raw_affiliation_string":"University of California, Davis, CA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"University of California, Davis, CA,#TAB#","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100600286","display_name":"Xing Li","orcid":"https://orcid.org/0000-0002-5306-1742"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Li","raw_affiliation_strings":["Tsinghua University, Beijing, P.R.China","TsingHua University, Beijing, P.R. China#TAB#"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, P.R.China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"TsingHua University, Beijing, P.R. China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035208775"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":8.6064,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.970649,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1094","last_page":"1098"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9739999771118164,"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":0.965399980545044,"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":0.8198553323745728},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7405697107315063},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.6810534596443176},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.6661204099655151},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5853037238121033},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.53458571434021},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5096836090087891},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.49593839049339294},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4493813216686249},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.43431320786476135},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4027852714061737},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.29526904225349426},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24866390228271484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198553323745728},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7405697107315063},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.6810534596443176},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.6661204099655151},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5853037238121033},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.53458571434021},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5096836090087891},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.49593839049339294},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4493813216686249},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.43431320786476135},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4027852714061737},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.29526904225349426},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24866390228271484},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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:10.1145/1141277.1141534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.60.4599","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.4599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wwwcsif.cs.ucdavis.edu/~yeshao/./sac06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1566513354","https://openalex.org/W1988121588","https://openalex.org/W1989338554","https://openalex.org/W2019264297","https://openalex.org/W2040075907","https://openalex.org/W2044958453","https://openalex.org/W2064716575","https://openalex.org/W2123845384","https://openalex.org/W2124436456","https://openalex.org/W2129595335","https://openalex.org/W2140204390","https://openalex.org/W2150721933","https://openalex.org/W2156632103","https://openalex.org/W2157316480","https://openalex.org/W2171500543"],"related_works":["https://openalex.org/W2121300814","https://openalex.org/W4231091074","https://openalex.org/W1886613375","https://openalex.org/W4236081792","https://openalex.org/W4250583430","https://openalex.org/W4234406076","https://openalex.org/W2010731026","https://openalex.org/W4311328601","https://openalex.org/W2360893094","https://openalex.org/W4390787808"],"abstract_inverted_index":{"Templates":[0],"in":[1,10],"web":[2,31,60,109],"sites":[3,110],"hurt":[4],"search":[5,57],"engine":[6],"retrieval":[7],"performance,":[8],"especially":[9],"content":[11,97],"relevance":[12],"and":[13,24,48,66,96,102,120],"link":[14],"analysis.":[15],"Current":[16],"template":[17,41,46],"removal":[18,49],"methods":[19,122],"suffer":[20],"from":[21],"processing":[22],"speed":[23],"scalability":[25],"when":[26],"dealing":[27],"with":[28,50,92,123],"large":[29],"volume":[30],"pages.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"propose":[37],"a":[38,56],"novel":[39],"two-stage":[40],"detection":[42,47],"method,":[43],"which":[44],"combines":[45],"the":[51,79,86],"index":[52,87],"building":[53,88],"process":[54],"of":[55],"engine.":[58],"First,":[59],"pages":[61],"are":[62,68,83,98],"segmented":[63],"into":[64],"blocks":[65,67,91],"clustered":[69],"according":[70],"to":[71],"their":[72],"style":[73,82,95],"features.":[74],"Second,":[75],"similar":[76,93],"contents":[77],"sharing":[78],"common":[80],"layout":[81,94],"detected":[84],"during":[85],"process.":[89],"The":[90],"identified":[99],"as":[100],"templates":[101],"deleted.":[103],"Our":[104],"experiment":[105],"on":[106],"eight":[107],"popular":[108],"shows":[111],"that":[112],"our":[113],"method":[114],"achieves":[115],"20-40%":[116],"faster":[117],"than":[118],"shingle":[119],"SST":[121],"close":[124],"accuracy.":[125]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}