{"id":"https://openalex.org/W1987187046","doi":"https://doi.org/10.1109/fskd.2010.5569236","title":"Combining topic models and string kernel for deep web categorization","display_name":"Combining topic models and string kernel for deep web categorization","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W1987187046","doi":"https://doi.org/10.1109/fskd.2010.5569236","mag":"1987187046"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2010.5569236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2010.5569236","pdf_url":null,"source":{"id":"https://openalex.org/S4363608217","display_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","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/A5101662156","display_name":"Guangyue Xu","orcid":"https://orcid.org/0000-0001-7229-8422"},"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":"Guangyue Xu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108050911","display_name":"Weimin Zheng","orcid":"https://orcid.org/0000-0002-4450-5428"},"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":"Weimin Zheng","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Dept. of Computer Science & Technology, Tsinghua University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002997318","display_name":"Haiping Wu","orcid":"https://orcid.org/0000-0003-1904-652X"},"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"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiping Wu","raw_affiliation_strings":["Division of Informatics, Graduate School, Shenzhen of Tsinghua University, Shenzhen, China","Division of Informatics, Graduate School at Shenzhen, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Division of Informatics, Graduate School, Shenzhen of Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Division of Informatics, Graduate School at Shenzhen, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020953714","display_name":"Yujiu Yang","orcid":"https://orcid.org/0000-0002-6427-1024"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Yujiu Yang","raw_affiliation_strings":["Division of Informatics, Graduate School, Shenzhen of Tsinghua University, Shenzhen, China","Division of Informatics, Graduate School at Shenzhen, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Division of Informatics, Graduate School, Shenzhen of Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Division of Informatics, Graduate School at Shenzhen, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101662156"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.4609,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69553806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"37","issue":null,"first_page":"2791","last_page":"2795"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9854000210762024,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9832000136375427,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8388391733169556},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.5901447534561157},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5841958522796631},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5617151856422424},{"id":"https://openalex.org/keywords/string-kernel","display_name":"String kernel","score":0.5547265410423279},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5325573682785034},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5156046748161316},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5052185654640198},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.48657166957855225},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46904903650283813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4634893238544464},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43611469864845276},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4323732554912567},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3622046113014221},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.34815675020217896},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.32962918281555176},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.23663127422332764},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.1759289801120758},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12447765469551086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8388391733169556},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.5901447534561157},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5841958522796631},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5617151856422424},{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.5547265410423279},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5325573682785034},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5156046748161316},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5052185654640198},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.48657166957855225},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46904903650283813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4634893238544464},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43611469864845276},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4323732554912567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3622046113014221},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.34815675020217896},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.32962918281555176},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.23663127422332764},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.1759289801120758},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12447765469551086},{"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/C160446489","wikidata":"https://www.wikidata.org/wiki/Q7226642","display_name":"Polynomial kernel","level":4,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2010.5569236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2010.5569236","pdf_url":null,"source":{"id":"https://openalex.org/S4363608217","display_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1516111018","https://openalex.org/W1659541576","https://openalex.org/W1880262756","https://openalex.org/W1915058860","https://openalex.org/W1968832971","https://openalex.org/W1969831559","https://openalex.org/W2001082470","https://openalex.org/W2012145396","https://openalex.org/W2053414435","https://openalex.org/W2107425660","https://openalex.org/W2107743791","https://openalex.org/W2116341550","https://openalex.org/W2120642948","https://openalex.org/W2123853152","https://openalex.org/W2125121047","https://openalex.org/W2130760429","https://openalex.org/W4231510805","https://openalex.org/W4233135949","https://openalex.org/W4285719527","https://openalex.org/W6639619044","https://openalex.org/W6639973174","https://openalex.org/W6676236601","https://openalex.org/W6677778574"],"related_works":["https://openalex.org/W152351265","https://openalex.org/W3042295250","https://openalex.org/W4319870840","https://openalex.org/W2163203700","https://openalex.org/W4206904133","https://openalex.org/W1986532736","https://openalex.org/W1975708617","https://openalex.org/W3013206934","https://openalex.org/W2020816856","https://openalex.org/W1835000624"],"abstract_inverted_index":{"Online":[0],"databases":[1],"maintain":[2],"a":[3,32,50,131],"collection":[4],"of":[5,17,150,203],"structured":[6],"domain-specific":[7],"documents":[8],"dynamically":[9],"generated":[10],"in":[11,56,122,176],"response":[12],"to":[13,27,35,104,116,137,143],"users'":[14],"queries":[15],"instead":[16],"being":[18],"accessed":[19],"by":[20],"static":[21],"URLs.":[22],"Categorizing":[23],"deep":[24,113,141],"webs":[25,114,142],"according":[26],"their":[28],"object":[29,85],"domains":[30],"is":[31,156],"critical":[33],"step":[34],"integrate":[36],"such":[37],"sources.":[38],"While":[39],"existing":[40],"methods":[41,136],"focus":[42],"on":[43,168,185],"supervised":[44],"or":[45],"post-query":[46],"methodologies,":[47],"we":[48,94,129,158],"propose":[49],"more":[51],"practical":[52],"pre-query":[53],"algorithm":[54,152],"operating":[55],"an":[57,177],"unsupervised":[58,178],"manner.":[59],"Given":[60],"the":[61,70,100,112,126,139,145,160,169,186,190,199],"domain":[62,72,86],"number,":[63],"our":[64,96,151,173,204],"two":[65,170],"phase":[66,171],"approach":[67],"firstly":[68],"investigates":[69],"hidden":[71],"distribution":[73],"for":[74,163],"each":[75,82,164],"query":[76,83,101,165],"form":[77],"using":[78],"topic":[79],"models":[80],"and":[81,110,180,201],"form's":[84],"can":[87],"be":[88,117],"identified":[89],"preliminarily.":[90],"In":[91,125],"this":[92,123],"phase,":[93,128],"construct":[95],"training":[97],"set":[98],"composing":[99],"forms":[102],"deemed":[103],"have":[105],"already":[106],"been":[107],"categorized":[108],"correctly,":[109],"beside,":[111],"needed":[115],"reclassified":[118],"are":[119],"also":[120],"selected":[121],"phase.":[124],"second":[127],"train":[130],"classifier":[132],"with":[133],"String":[134],"Kernel":[135],"reclassify":[138],"uncertain":[140],"improve":[144],"overall":[146],"performance.":[147],"The":[148],"advantage":[149],"over":[153],"previous":[154],"ones":[155],"that":[157],"capture":[159],"semantic":[161],"structure":[162],"form.":[166],"Based":[167],"architecture,":[172],"framework":[174],"works":[175],"manner":[179],"achieves":[181],"satisfactory":[182],"results.":[183],"Experiments":[184],"TEL-8":[187],"dataset":[188],"from":[189],"UIUC":[191],"Web":[192],"integration":[193],"repository":[194],"<sup":[195],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[196],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[197],"show":[198],"effectiveness":[200],"efficiency":[202],"algorithm.":[205]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}