{"id":"https://openalex.org/W2073030376","doi":"https://doi.org/10.1145/1062745.1062892","title":"Site abstraction for rare category classification in large-scale web directory","display_name":"Site abstraction for rare category classification in large-scale web directory","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2073030376","doi":"https://doi.org/10.1145/1062745.1062892","mag":"2073030376"},"language":"en","primary_location":{"id":"doi:10.1145/1062745.1062892","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web  - WWW '05","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Tie-Yan LIU","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P. R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103181518","display_name":"Hao Wan","orcid":"https://orcid.org/0000-0001-7188-2803"},"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":"Hao WAN","raw_affiliation_strings":["Tsinghua University Beijing, P.R. China","TsingHua University, Beijing, P.R. China#TAB#"],"raw_orcid":null,"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/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"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":"Tao QIN","raw_affiliation_strings":["Tsinghua University Beijing, P.R. China","TsingHua University, Beijing, P.R. China#TAB#"],"raw_orcid":null,"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/A5088372348","display_name":"Zheng Chen","orcid":"https://orcid.org/0000-0003-4013-3492"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Zheng CHEN","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P. R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002346706","display_name":"Yong Ren","orcid":"https://orcid.org/0000-0003-0312-9371"},"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":"Yong REN","raw_affiliation_strings":["Tsinghua University Beijing, P.R. China","TsingHua University, Beijing, P.R. China#TAB#"],"raw_orcid":null,"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":"last","author":{"id":"https://openalex.org/A5103733614","display_name":"Wei\u2010Ying Ma","orcid":"https://orcid.org/0000-0002-7384-0735"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wei-Ying MA","raw_affiliation_strings":["Microsoft Research Asia, Beijing, P. R. China","[Microsoft Research Asia, Beijing, P.R. China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, P. R. China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"[Microsoft Research Asia, Beijing, P.R. China]","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1108","last_page":"1108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.995199978351593,"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":0.8319334983825684},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.8042696714401245},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.7197806239128113},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6303558945655823},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5766919255256653},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4730704724788666},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.458234578371048},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4202742576599121},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35966235399246216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319334983825684},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.8042696714401245},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7197806239128113},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6303558945655823},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5766919255256653},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4730704724788666},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.458234578371048},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4202742576599121},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35966235399246216},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1062745.1062892","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1062745.1062892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special interest tracks and posters of the 14th international conference on World Wide Web  - WWW '05","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W17548503","https://openalex.org/W1488890239","https://openalex.org/W1523949738","https://openalex.org/W2063862666","https://openalex.org/W2070920590","https://openalex.org/W2072183822","https://openalex.org/W2150102617"],"related_works":["https://openalex.org/W3115906952","https://openalex.org/W3134811395","https://openalex.org/W3155196058","https://openalex.org/W4252960523","https://openalex.org/W1529821365","https://openalex.org/W2135486207","https://openalex.org/W1499611046","https://openalex.org/W3024420453","https://openalex.org/W2388608119","https://openalex.org/W2915494741"],"abstract_inverted_index":{"Automatically":[0],"classifying":[1],"the":[2,18,36,40,70,73,88,98],"Web":[3,11,50],"directories":[4],"is":[5,39,80],"an":[6],"effective":[7,43],"way":[8],"to":[9,26,33,64,81],"manage":[10],"information.":[12],"However,":[13],"our":[14,34,94],"experiments":[15],"showed":[16,92],"that":[17,93],"state-of-the-art":[19],"text":[20],"classification":[21,99],"technologies":[22],"could":[23],"not":[24],"lead":[25],"acceptable":[27],"performance":[28],"in":[29,46,87],"this":[30,54],"task.":[31],"Due":[32],"analysis,":[35],"main":[37,78],"problem":[38],"lack":[41],"of":[42,49,72],"training":[44,67,75],"data":[45],"rare":[47],"categories":[48],"directories.":[51],"To":[52],"tackle":[53],"problem,":[55],"we":[56],"proposed":[57],"a":[58],"novel":[59],"technology":[60],"named":[61],"Site":[62],"Abstraction":[63],"synthesize":[65],"new":[66],"examples":[68],"from":[69],"website":[71],"existing":[74],"document.":[76],"The":[77],"idea":[79],"propagate":[82],"features":[83],"through":[84],"parent-child":[85],"relationship":[86],"sitemap":[89],"tree.":[90],"Experiments":[91],"method":[95],"significantly":[96],"improved":[97],"performance.":[100]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}