{"id":"https://openalex.org/W1974346290","doi":"https://doi.org/10.1145/1774088.1774445","title":"Wikipedia driven autonomous label assignment in wrapper induced tables with missing column names","display_name":"Wikipedia driven autonomous label assignment in wrapper induced tables with missing column names","publication_year":2010,"publication_date":"2010-03-22","ids":{"openalex":"https://openalex.org/W1974346290","doi":"https://doi.org/10.1145/1774088.1774445","mag":"1974346290"},"language":"en","primary_location":{"id":"doi:10.1145/1774088.1774445","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM Symposium on Applied Computing","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/A5056136571","display_name":"Mohammad Shafkat Amin","orcid":null},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammad Shafkat Amin","raw_affiliation_strings":["Wayne State University"],"affiliations":[{"raw_affiliation_string":"Wayne State University","institution_ids":["https://openalex.org/I185443292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027791481","display_name":"Anupam Bhattacharjee","orcid":null},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anupam Bhattacharjee","raw_affiliation_strings":["Wayne State University"],"affiliations":[{"raw_affiliation_string":"Wayne State University","institution_ids":["https://openalex.org/I185443292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030091324","display_name":"Hasan M. Jamil","orcid":"https://orcid.org/0000-0002-3124-3780"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hasan Jamil","raw_affiliation_strings":["Wayne State University"],"affiliations":[{"raw_affiliation_string":"Wayne State University","institution_ids":["https://openalex.org/I185443292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056136571"],"corresponding_institution_ids":["https://openalex.org/I185443292"],"apc_list":null,"apc_paid":null,"fwci":0.6937,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81288585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1656","last_page":"1660"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9944000244140625,"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/T11719","display_name":"Data Quality and Management","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8293737173080444},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.7566884756088257},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7208781838417053},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6813206672668457},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6478387117385864},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.528965413570404},{"id":"https://openalex.org/keywords/decipher","display_name":"DECIPHER","score":0.4304627478122711},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.42331042885780334},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.42020943760871887},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34535059332847595},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.29797422885894775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2929084897041321}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293737173080444},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.7566884756088257},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7208781838417053},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6813206672668457},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6478387117385864},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.528965413570404},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.4304627478122711},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.42331042885780334},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.42020943760871887},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34535059332847595},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29797422885894775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2929084897041321},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1774088.1774445","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1774088.1774445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4013050433","display_name":null,"funder_award_id":"CNS 0521454IIS 0612203","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"},{"id":"https://openalex.org/G8528476289","display_name":null,"funder_award_id":"CNS 0521454IIS 0612203","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W113372867","https://openalex.org/W126044612","https://openalex.org/W158057341","https://openalex.org/W1780933788","https://openalex.org/W1960027552","https://openalex.org/W1998089058","https://openalex.org/W2067416210","https://openalex.org/W2069388662","https://openalex.org/W2100341149","https://openalex.org/W2104086170","https://openalex.org/W2128836931","https://openalex.org/W2137653635","https://openalex.org/W2147032226","https://openalex.org/W2148210463","https://openalex.org/W2150721933","https://openalex.org/W2160196229","https://openalex.org/W2170626955","https://openalex.org/W4230770720"],"related_works":["https://openalex.org/W2115350162","https://openalex.org/W2330145053","https://openalex.org/W4249875204","https://openalex.org/W2416520078","https://openalex.org/W4242620632","https://openalex.org/W4256069380","https://openalex.org/W4379618494","https://openalex.org/W2113606293","https://openalex.org/W3123448197","https://openalex.org/W1510114644"],"abstract_inverted_index":{"As":[0],"the":[1,7,57,71,127,130,135,139,142,150,156,170,186,197,213,221,237,242],"volume":[2],"of":[3,17,129,141,172,188,223,235,241],"information":[4,19,32,58,78,115,137,151],"available":[5],"on":[6],"internet":[8],"is":[9,13,50,110,123,145,153,167],"growing":[10],"exponentially,":[11],"it":[12,49,109],"clear":[14],"that":[15,52,228],"most":[16,37],"this":[18,163,229],"will":[20,55,66],"have":[21],"to":[22,29,60,69,94,113,125,168,174,231],"be":[23,67],"processed":[24],"and":[25,65,133,158,239,245],"digested":[26],"by":[27,181,209],"computers":[28],"produce":[30],"useful":[31],"for":[33,43,107,185,212,216,220],"human":[34,45,54],"consumption.":[35],"Unfortunately,":[36],"web":[38,198],"contents":[39],"are":[40,102],"currently":[41],"designed":[42],"direct":[44],"consumption":[46],"in":[47,62,80,97,116,119,138,191,199],"which":[48,120],"assumed":[51],"a":[53,121,183,200,206,247],"decipher":[56],"presented":[59,79,132],"him":[61],"some":[63,81],"context":[64,140,238],"able":[68],"connect":[70],"missing":[72,178],"dots,":[73],"if":[74],"any.":[75],"In":[76,162],"particular,":[77],"tabular":[82],"form":[83],"often":[84],"does":[85],"not":[86,103],"accompany":[87],"descriptive":[88],"titles":[89],"or":[90],"column":[91,179,217],"names":[92,96,180,190],"similar":[93],"attribute":[95],"tables.":[98],"While":[99],"such":[100],"omissions":[101],"really":[104],"an":[105,192,232],"issue":[106,171],"humans,":[108],"truly":[111],"hard":[112],"extract":[114,134],"autonomous":[117,202],"systems":[118],"machine":[122],"expected":[124],"understand":[126],"meaning":[128],"table":[131,194,224,243],"right":[136],"query.":[143],"It":[144],"even":[146],"more":[147],"difficult":[148],"when":[149],"needed":[152],"distributed":[154],"across":[155],"globe":[157],"involve":[159],"semantic":[160],"heterogeneity.":[161],"paper,":[164],"our":[165],"goal":[166],"address":[169],"how":[173],"interpret":[175],"tables":[176],"with":[177],"developing":[182],"method":[184],"assignment":[187],"attributes":[189],"arbitrary":[193],"extracted":[195],"from":[196],"fully":[201],"manner.":[203],"We":[204,226],"propose":[205],"novel":[207],"approach":[208],"leveraging":[210],"Wikipedia":[211],"first":[214],"time":[215],"name":[218],"discovery":[219],"purpose":[222],"annotation.":[225],"show":[227],"leads":[230],"improved":[233],"likelihood":[234],"capturing":[236],"interpretation":[240],"accurately":[244],"producing":[246],"semantically":[248],"meaningful":[249],"query":[250],"response.":[251]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
