{"id":"https://openalex.org/W1994966918","doi":"https://doi.org/10.1145/1367497.1367628","title":"Can chinese web pages be classified with english data source?","display_name":"Can chinese web pages be classified with english data source?","publication_year":2008,"publication_date":"2008-04-21","ids":{"openalex":"https://openalex.org/W1994966918","doi":"https://doi.org/10.1145/1367497.1367628","mag":"1994966918"},"language":"en","primary_location":{"id":"doi:10.1145/1367497.1367628","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367628","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 international conference on World Wide Web","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/A5101476674","display_name":"Ling Xiao","orcid":"https://orcid.org/0000-0002-4650-8841"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Ling","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109845737","display_name":"Gui-Rong Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gui-Rong Xue","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100527530","display_name":"Wenyuan Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyuan Dai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101428417","display_name":"Yun Jiang","orcid":"https://orcid.org/0000-0002-2922-8872"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Jiang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636286","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0001-5059-8360"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong","Hong Kong University Of Science And Technology, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University Of Science And Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001571390","display_name":"Yong Yu","orcid":"https://orcid.org/0000-0003-0281-8271"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":123,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"969","last_page":"978"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9941999912261963,"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":0.9941999912261963,"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":0.993399977684021,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9388999938964844,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8358938694000244},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6949247121810913},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.605820894241333},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.6036080718040466},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.563986599445343},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5557644367218018},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.5132929682731628},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.46168914437294006},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.45450741052627563},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.43201470375061035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3325474262237549},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.3110339641571045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8358938694000244},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6949247121810913},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.605820894241333},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.6036080718040466},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.563986599445343},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5557644367218018},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.5132929682731628},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.46168914437294006},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.45450741052627563},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.43201470375061035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3325474262237549},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.3110339641571045},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1367497.1367628","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367628","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 international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.9330","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.9330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ust.hk/~qyang/Docs/2008/p969-ling.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.216.6876","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.216.6876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.washington.edu/homes/xiaoling/www08.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-20168","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-20168","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W87516236","https://openalex.org/W1489959797","https://openalex.org/W1493526108","https://openalex.org/W1504694836","https://openalex.org/W1594962278","https://openalex.org/W1965555277","https://openalex.org/W2048679005","https://openalex.org/W2064885744","https://openalex.org/W2087347434","https://openalex.org/W2097089247","https://openalex.org/W2098162425","https://openalex.org/W2099031744","https://openalex.org/W2099111195","https://openalex.org/W2107008379","https://openalex.org/W2116441169","https://openalex.org/W2122111042","https://openalex.org/W2126599826","https://openalex.org/W2136504847","https://openalex.org/W2138072998","https://openalex.org/W2139542376","https://openalex.org/W2140500610","https://openalex.org/W2145631291","https://openalex.org/W2155942458","https://openalex.org/W2164363339","https://openalex.org/W2434205482","https://openalex.org/W2435251607","https://openalex.org/W2914859268","https://openalex.org/W2979454998","https://openalex.org/W6629242371","https://openalex.org/W6637108112","https://openalex.org/W6678639768","https://openalex.org/W6680140577"],"related_works":["https://openalex.org/W132269582","https://openalex.org/W2800499880","https://openalex.org/W2015727217","https://openalex.org/W163338125","https://openalex.org/W2415191659","https://openalex.org/W2744329849","https://openalex.org/W2567626003","https://openalex.org/W2563863560","https://openalex.org/W4224286275","https://openalex.org/W2472862012"],"abstract_inverted_index":{"As":[0],"the":[1,26,43,116,124,157,172,180,189],"World":[2],"Wide":[3],"Web":[4,13,21,47,65,93,118,125,164,190],"in":[5,11,71,147],"China":[6],"grows":[7],"rapidly,":[8],"mining":[9],"knowledge":[10],"Chinese":[12,46,55,83,92,117,128,161],"pages":[14,48,119,165,191],"becomes":[15],"more":[16,18],"and":[17,85,129,162,210],"important.":[19],"Mining":[20],"information":[22,81,101,136,143,154],"usually":[23],"relies":[24],"on":[25],"machine":[27],"learning":[28],"techniques":[29],"which":[30,138,178],"require":[31],"a":[32,76],"large":[33],"amount":[34,78],"of":[35,45,79],"labeled":[36,56,64,68],"data":[37],"to":[38,89,105,120,144,149,168,171],"train":[39],"credible":[40],"models.":[41],"Although":[42],"number":[44],"increases":[49],"quite":[50],"fast,":[51],"it":[52],"still":[53],"lacks":[54],"data.":[57],"However,":[58],"there":[59],"are":[60,132],"relatively":[61],"sufficient":[62],"English":[63,130,163],"pages.":[66,94],"These":[67],"data,":[69],"though":[70],"different":[72],"linguistic":[73],"representations,":[74],"share":[75],"substantial":[77],"semantic":[80],"with":[82],"ones,":[84,131],"can":[86,139],"be":[87,169],"utilized":[88],"help":[90],"classify":[91],"In":[95],"this":[96,107],"paper,":[97],"we":[98],"propose":[99],"an":[100,135],"bottleneck":[102,137],"based":[103],"approach":[104,187],"address":[106],"cross-language":[108,181],"classification":[109,182],"problem.":[110],"Our":[111],"algorithm":[112],"first":[113],"translates":[114],"all":[115,123],"English.":[121],"Then,":[122],"pages,":[126],"including":[127],"encoded":[133,170],"through":[134],"allow":[140],"only":[141],"limited":[142],"pass.":[145],"Therefore,":[146],"order":[148],"retain":[150],"as":[151,155],"much":[152],"useful":[153],"possible,":[156],"common":[158],"part":[159],"between":[160],"is":[166],"inclined":[167],"same":[173],"code":[174],"(i.e.":[175],"class":[176],"label),":[177],"makes":[179],"accurate.":[183],"We":[184],"evaluated":[185],"our":[186,203],"using":[188],"collected":[192],"from":[193],"Open":[194],"Directory":[195],"Project":[196],"(ODP).":[197],"The":[198],"experimental":[199],"results":[200],"show":[201],"that":[202],"method":[204],"significantly":[205],"improves":[206],"several":[207],"existing":[208],"supervised":[209],"semi-supervised":[211],"classifiers.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":15}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
