{"id":"https://openalex.org/W2091224712","doi":"https://doi.org/10.1145/2063576.2063847","title":"Extract knowledge from semi-structured websites for search task simplification","display_name":"Extract knowledge from semi-structured websites for search task simplification","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W2091224712","doi":"https://doi.org/10.1145/2063576.2063847","mag":"2091224712"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063847","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","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/A5047014488","display_name":"Yingqin Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingqin Gu","raw_affiliation_strings":["Renmin University of China, Beijing, China","Renmin Univ. of China, Beijing - China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Renmin Univ. of China, Beijing - China#TAB#","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055987663","display_name":"Jun Yan","orcid":"https://orcid.org/0000-0002-6474-1049"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Jun Yan","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332465","display_name":"Hongyan Liu","orcid":"https://orcid.org/0000-0002-4902-1078"},"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":"Hongyan Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766741","display_name":"Jun He","orcid":"https://orcid.org/0000-0003-1511-7554"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun He","raw_affiliation_strings":["Renmin University of China, Beijing, China","Renmin Univ. of China, Beijing - China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Renmin Univ. of China, Beijing - China#TAB#","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100754485","display_name":"Lei Ji","orcid":"https://orcid.org/0000-0002-7569-3265"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Lei Ji","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101718710","display_name":"Ning Liu","orcid":"https://orcid.org/0000-0002-3622-9400"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Ning Liu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100370688","display_name":"Zheng Chen","orcid":"https://orcid.org/0000-0003-0961-8758"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Zheng Chen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2924,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91246945,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1883","last_page":"1888"},"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":0.9793999791145325,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9783999919891357,"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":0.8305020332336426},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8062568306922913},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6796585321426392},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6114009618759155},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5733016729354858},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5457876920700073},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.46631819009780884},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34249165654182434},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34133052825927734},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2160491943359375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305020332336426},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8062568306922913},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6796585321426392},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6114009618759155},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5733016729354858},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5457876920700073},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.46631819009780884},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34249165654182434},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34133052825927734},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2160491943359375},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2063576.2063847","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1489949474","https://openalex.org/W1493490255","https://openalex.org/W2038994299","https://openalex.org/W2093559286","https://openalex.org/W2104086170","https://openalex.org/W2128341918","https://openalex.org/W2140602286","https://openalex.org/W2148540243","https://openalex.org/W2150721933","https://openalex.org/W2152986551"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W2011430815","https://openalex.org/W4321606653"],"abstract_inverted_index":{"Simplifying":[0],"the":[1,38,42,71,82,91,115,149],"key":[2,140],"tasks":[3],"of":[4,30,103],"search":[5,141],"engine":[6],"users":[7,136],"by":[8,114],"directly":[9],"retrieving":[10],"to":[11,16,36,88,109,130,134],"them":[12],"structured":[13,39,132],"knowledge":[14,40,133],"according":[15],"their":[17,139],"queries":[18],"is":[19,34,107],"attracting":[20],"much":[21],"attention":[22],"from":[23,41,66,90],"both":[24],"industry":[25],"and":[26,44,76,112],"academia.":[27],"A":[28],"bottleneck":[29],"this":[31,51],"challenging":[32],"problem":[33],"how":[35],"extract":[37],"noisy":[43],"complex":[45],"Web":[46,104],"scale":[47],"websites":[48],"automatically.":[49],"In":[50],"paper,":[52],"we":[53,125],"propose":[54],"an":[55],"unsupervised":[56],"automatic":[57],"wrapper":[58,72,84],"induction":[59],"algorithm,":[60],"named":[61],"as":[62,99],"Scalable":[63],"Knowledge":[64],"Extractor":[65],"webSites":[67],"(SKES).":[68],"SKES":[69,106],"induces":[70],"in":[73],"a":[74,128],"divide":[75],"conquer":[77],"mode,":[78],"i.e.,":[79],"it":[80],"divides":[81],"general":[83],"into":[85],"several":[86],"sub-wrappers":[87],"learn":[89],"data":[92],"independently.":[93],"Moreover,":[94],"through":[95],"employing":[96],"techniques":[97],"such":[98],"tag":[100],"path":[101],"representation":[102],"pages,":[105],"verified":[108],"be":[110],"efficient":[111],"noise-tolerant":[113],"experimental":[116],"results.":[117],"Furthermore,":[118],"based":[119],"on":[120,148],"our":[121],"automatically":[122],"extracted":[123],"knowledge,":[124],"also":[126],"built":[127],"prototype":[129],"serve":[131],"end":[135],"for":[137],"simplifying":[138],"tasks.":[142],"Very":[143],"positive":[144],"feedbacks":[145],"were":[146],"received":[147],"prototype.":[150]},"counts_by_year":[{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}