{"id":"https://openalex.org/W2072824140","doi":"https://doi.org/10.1145/1081870.1081905","title":"Web object indexing using domain knowledge","display_name":"Web object indexing using domain knowledge","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W2072824140","doi":"https://doi.org/10.1145/1081870.1081905","mag":"2072824140"},"language":"en","primary_location":{"id":"doi:10.1145/1081870.1081905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","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/A5021298669","display_name":"Muyuan Wang","orcid":null},"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":"Muyuan Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409062","display_name":"Zhiwei Li","orcid":"https://orcid.org/0000-0001-7071-199X"},"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":"Zhiwei Li","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"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/A5110491600","display_name":"Lie Lu","orcid":null},"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":"Lie Lu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"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/A5103733614","display_name":"Wei\u2010Ying Ma","orcid":"https://orcid.org/0000-0002-7384-0735"},"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":"Wei-Ying Ma","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"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/A5032542621","display_name":"Naiyao Zhang","orcid":null},"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":"Naiyao Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021298669"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8053,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84577233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"294","last_page":"303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9980000257492065,"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":0.9980000257492065,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9925000071525574,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9884999990463257,"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":0.8221209049224854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6423678398132324},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5973126888275146},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5433228611946106},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.5300034284591675},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.5293358564376831},{"id":"https://openalex.org/keywords/social-semantic-web","display_name":"Social Semantic Web","score":0.48723188042640686},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.4852862060070038},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4705370366573334},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.44175484776496887},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.36851823329925537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15682902932167053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221209049224854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6423678398132324},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5973126888275146},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5433228611946106},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.5300034284591675},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.5293358564376831},{"id":"https://openalex.org/C534406577","wikidata":"https://www.wikidata.org/wiki/Q7550843","display_name":"Social Semantic Web","level":3,"score":0.48723188042640686},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.4852862060070038},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4705370366573334},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.44175484776496887},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.36851823329925537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15682902932167053}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1081870.1081905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1081870.1081905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining","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":13,"referenced_works":["https://openalex.org/W1528332570","https://openalex.org/W1572278817","https://openalex.org/W1803802947","https://openalex.org/W2079672501","https://openalex.org/W2098388305","https://openalex.org/W2105567784","https://openalex.org/W2113112851","https://openalex.org/W2136016364","https://openalex.org/W2138621811","https://openalex.org/W2147152072","https://openalex.org/W2221667243","https://openalex.org/W2914933231","https://openalex.org/W4240407914"],"related_works":["https://openalex.org/W2305384628","https://openalex.org/W2963140294","https://openalex.org/W1495666889","https://openalex.org/W4249203355","https://openalex.org/W2111508211","https://openalex.org/W4230517744","https://openalex.org/W2561758991","https://openalex.org/W2042825220","https://openalex.org/W2024646113","https://openalex.org/W1510354227"],"abstract_inverted_index":{"A":[0],"web":[1,12,42,50,64,115,136,154,171],"object":[2,9,51,65,116,137,155],"is":[3,118,142],"defined":[4],"to":[5,19,31,63,98,126,146,166,181,187],"represent":[6],"any":[7],"meaningful":[8],"embedded":[10],"in":[11,55,96,106,144],"pages":[13],"(e.g.":[14,22],"images,":[15],"music)":[16],"or":[17],"pointed":[18],"by":[20,67,120],"hyperlinks":[21],"downloadable":[23],"files).":[24],"In":[25,77],"many":[26],"cases,":[27],"users":[28],"would":[29],"like":[30],"search":[32],"for":[33,86],"information":[34,72,191],"of":[35,90,109,152,192],"a":[36,41,60,87,177],"certain":[37],"'object',":[38],"rather":[39],"than":[40],"page":[43],"containing":[44],"the":[45,91,100,110,114,128,135,139,149,153,157,160,170],"query":[46],"terms.":[47],"To":[48],"facilitate":[49],"searching":[52],"and":[53,103,123,138,168],"organizing,":[54],"this":[56],"paper,":[57],"we":[58],"propose":[59],"novel":[61],"approach":[62,174],"indexing,":[66],"discovering":[68],"its":[69],"inherent":[70],"structure":[71,150,162],"with":[73],"existed":[74],"domain":[75,94,111,140],"knowledge.":[76,112,158],"our":[78],"approach,":[79],"first,":[80],"Layered":[81],"LSI":[82],"spaces":[83],"are":[84,164],"built":[85],"better":[88],"representation":[89,117],"hierarchically":[92],"structured":[93],"knowledge,":[95],"order":[97,145],"emphasize":[99],"specific":[101],"semantics":[102],"term":[104],"space":[105],"each":[107],"layer":[108],"Meanwhile,":[113],"constructed":[119],"hyperlink":[121],"analysis,":[122],"further":[124],"pruned":[125],"remove":[127],"noises.":[129],"Then":[130],"an":[131],"optimal":[132],"matching":[133],"between":[134],"knowledge":[141,186],"performed,":[143],"pick":[147],"out":[148],"attributes":[151,163],"from":[156],"Finally,":[159],"obtained":[161],"used":[165],"re-organize":[167],"index":[169],"objects.":[172],"Our":[173],"also":[175],"indicates":[176],"new":[178],"promising":[179],"way":[180],"use":[182],"trust-worthy":[183],"Deep":[184],"Web":[185],"help":[188],"organize":[189],"dispersive":[190],"Surface":[193],"Web.":[194]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}