{"id":"https://openalex.org/W2015415022","doi":"https://doi.org/10.1145/1298406.1298438","title":"Clustering web documents with tables for information extraction","display_name":"Clustering web documents with tables for information extraction","publication_year":2007,"publication_date":"2007-10-28","ids":{"openalex":"https://openalex.org/W2015415022","doi":"https://doi.org/10.1145/1298406.1298438","mag":"2015415022"},"language":"en","primary_location":{"id":"doi:10.1145/1298406.1298438","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1298406.1298438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th international conference on Knowledge capture","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/A5112547698","display_name":"Kostyantyn Shchekotykhin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166741","display_name":"University of Klagenfurt","ror":"https://ror.org/05q9m0937","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210166741"]},{"id":"https://openalex.org/I134023368","display_name":"Institute for Interdisciplinary Studies of Austrian Universities","ror":"https://ror.org/001zf8v27","country_code":"AT","type":"education","lineage":["https://openalex.org/I134023368","https://openalex.org/I4210166741"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Kostyantyn Shchekotykhin","raw_affiliation_strings":["University of Klagenfurt, Klagenfurt, Austria","[University of Klagenfurt, Klagenfurt, Austria]"],"affiliations":[{"raw_affiliation_string":"University of Klagenfurt, Klagenfurt, Austria","institution_ids":["https://openalex.org/I4210166741"]},{"raw_affiliation_string":"[University of Klagenfurt, Klagenfurt, Austria]","institution_ids":["https://openalex.org/I134023368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005545405","display_name":"Dietmar Jannach","orcid":"https://orcid.org/0000-0002-4698-8507"},"institutions":[{"id":"https://openalex.org/I4210166741","display_name":"University of Klagenfurt","ror":"https://ror.org/05q9m0937","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210166741"]},{"id":"https://openalex.org/I134023368","display_name":"Institute for Interdisciplinary Studies of Austrian Universities","ror":"https://ror.org/001zf8v27","country_code":"AT","type":"education","lineage":["https://openalex.org/I134023368","https://openalex.org/I4210166741"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Dietmar Jannach","raw_affiliation_strings":["University of Klagenfurt, Klagenfurt, Austria","[University of Klagenfurt, Klagenfurt, Austria]"],"affiliations":[{"raw_affiliation_string":"University of Klagenfurt, Klagenfurt, Austria","institution_ids":["https://openalex.org/I4210166741"]},{"raw_affiliation_string":"[University of Klagenfurt, Klagenfurt, Austria]","institution_ids":["https://openalex.org/I134023368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037543382","display_name":"Gerhard Friedrich","orcid":"https://orcid.org/0000-0002-1992-4049"},"institutions":[{"id":"https://openalex.org/I4210166741","display_name":"University of Klagenfurt","ror":"https://ror.org/05q9m0937","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210166741"]},{"id":"https://openalex.org/I134023368","display_name":"Institute for Interdisciplinary Studies of Austrian Universities","ror":"https://ror.org/001zf8v27","country_code":"AT","type":"education","lineage":["https://openalex.org/I134023368","https://openalex.org/I4210166741"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Friedrich","raw_affiliation_strings":["University of Klagenfurt, Klagenfurt, Austria","[University of Klagenfurt, Klagenfurt, Austria]"],"affiliations":[{"raw_affiliation_string":"University of Klagenfurt, Klagenfurt, Austria","institution_ids":["https://openalex.org/I4210166741"]},{"raw_affiliation_string":"[University of Klagenfurt, Klagenfurt, Austria]","institution_ids":["https://openalex.org/I134023368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112547698"],"corresponding_institution_ids":["https://openalex.org/I134023368","https://openalex.org/I4210166741"],"apc_list":null,"apc_paid":null,"fwci":4.9699,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.95051332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991000294685364,"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":0.9991000294685364,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9847000241279602,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9846000075340271,"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":0.8745689392089844},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.752282977104187},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7006790637969971},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5662310123443604},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5591316223144531},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.5221288800239563},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4757551848888397},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.475154846906662},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4686787724494934},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45711827278137207},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.44020816683769226},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42862969636917114},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.42654553055763245},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.4100441634654999},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40176665782928467},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2698555588722229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19876721501350403},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.15819555521011353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8745689392089844},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.752282977104187},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7006790637969971},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5662310123443604},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5591316223144531},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.5221288800239563},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4757551848888397},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.475154846906662},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4686787724494934},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45711827278137207},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.44020816683769226},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42862969636917114},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.42654553055763245},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4100441634654999},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40176665782928467},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2698555588722229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19876721501350403},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.15819555521011353},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1298406.1298438","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1298406.1298438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th international conference on Knowledge capture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.68.4398","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.68.4398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.configworks.com/dj/Conference_KCAP_2007.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323031","display_name":"\u00d6sterreichische Forschungsf\u00f6rderungsgesellschaft","ror":"https://ror.org/028jc0449"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1585610988","https://openalex.org/W2100684772"],"related_works":["https://openalex.org/W2384033143","https://openalex.org/W3005260231","https://openalex.org/W2067523177","https://openalex.org/W2371933330","https://openalex.org/W2111427713","https://openalex.org/W2166029629","https://openalex.org/W2340568692","https://openalex.org/W3163287122","https://openalex.org/W2388186172","https://openalex.org/W2972160875"],"abstract_inverted_index":{"One":[0],"of":[1,17,103,128,189,203],"the":[2,15,18,45,166,183],"common":[3,126],"approaches":[4],"to":[5,13,29,38,50,73,83,152,164,177],"extracting":[6],"high-quality":[7],"knowledge":[8,54],"from":[9],"Web":[10,23,33],"sources":[11],"is":[12,90,97],"exploit":[14],"redundancy":[16],"published":[19],"information.":[20,86],"Therefore,":[21],"a":[22,70,100,124,141],"Mining":[24],"System":[25],"not":[26],"only":[27],"has":[28,37,60],"search":[30],"for":[31,98,155],"relevant":[32],"pages":[34,43],"but":[35],"also":[36],"somehow":[39],"determine":[40,178],"whether":[41,179],"two":[42,180,193],"describe":[44,132,182],"same":[46,184],"entity":[47,156],"in":[48,68,92,106,192,201],"order":[49],"extract":[51,153],"as":[52,55,117],"much":[53],"possible":[56],"about":[57],"it.":[58],"It":[59],"been":[61],"shown":[62],"that":[63,80,146],"statistical":[64],"clustering":[65,112,144],"techniques":[66],"are":[67,81,161,174],"general":[69],"suitable":[71],"means":[72],"achieve":[74],"this":[75,136],"task":[76],"by":[77],"grouping":[78],"documents":[79,118,167,181],"supposed":[82],"contain":[84],"similar":[85],"However,":[87],"when":[88],"data":[89],"given":[91],"tabular":[93,120],"form":[94],"-":[95,109],"which":[96,173],"instance":[99],"typical":[101],"way":[102],"describing":[104],"items":[105],"online":[107],"shops":[108],"existing":[110],"document":[111,143,150],"algorithms":[113],"show":[114],"limited":[115],"performance":[116],"containing":[119],"descriptions":[121],"typically":[122],"share":[123],"very":[125],"set":[127],"tokens":[129],"although":[130],"they":[131],"different":[133],"entities.":[134],"In":[135],"paper":[137],"we":[138],"therefore":[139],"propose":[140],"new":[142],"approach":[145,191],"exploits":[147],"hyperlinks":[148],"and":[149,168,205],"metadata":[151],"candidates":[154],"names.":[157],"These":[158],"candidate":[159],"names":[160],"subsequently":[162],"used":[163,176],"cluster":[165],"further":[169],"improve":[170],"these":[171],"names,":[172],"finally":[175],"entity.":[185],"The":[186],"detailed":[187],"evaluation":[188],"our":[190],"popular":[194],"example":[195],"domains":[196],"showed":[197],"its":[198],"high":[199],"accuracy":[200],"terms":[202],"precision":[204],"recall":[206],"(F-Measure":[207],">":[208],"0.9).":[209]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
