{"id":"https://openalex.org/W3208057978","doi":"https://doi.org/10.1145/3459637.3482295","title":"Semantic Concept Annotation for Tabular Data","display_name":"Semantic Concept Annotation for Tabular Data","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3208057978","doi":"https://doi.org/10.1145/3459637.3482295","mag":"3208057978"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","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/A5013455098","display_name":"Udayan Khurana","orcid":"https://orcid.org/0000-0001-8113-1210"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Udayan Khurana","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038532934","display_name":"Sainyam Galhotra","orcid":"https://orcid.org/0000-0003-2529-4036"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sainyam Galhotra","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013455098"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":2.2656,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88171673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"844","last_page":"853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9983999729156494,"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/T11106","display_name":"Data Management and Algorithms","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8568912744522095},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6315152645111084},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5665321946144104},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5165938138961792},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.4944016933441162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46476611495018005},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.45231714844703674},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44957882165908813},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.44951772689819336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42187023162841797},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39773738384246826},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34953123331069946},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17295879125595093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568912744522095},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6315152645111084},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5665321946144104},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5165938138961792},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.4944016933441162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46476611495018005},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.45231714844703674},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44957882165908813},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.44951772689819336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42187023162841797},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39773738384246826},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34953123331069946},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17295879125595093},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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:10.1145/3459637.3482295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","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":34,"referenced_works":["https://openalex.org/W1534477342","https://openalex.org/W2008896880","https://openalex.org/W2020022499","https://openalex.org/W2064766209","https://openalex.org/W2092364718","https://openalex.org/W2111869785","https://openalex.org/W2114123275","https://openalex.org/W2154658848","https://openalex.org/W2162020046","https://openalex.org/W2341748398","https://openalex.org/W2521441617","https://openalex.org/W2762307198","https://openalex.org/W2789111643","https://openalex.org/W2898629972","https://openalex.org/W2898796029","https://openalex.org/W2941366772","https://openalex.org/W2950133940","https://openalex.org/W2951621897","https://openalex.org/W2965875055","https://openalex.org/W2999876407","https://openalex.org/W3013003636","https://openalex.org/W3013427466","https://openalex.org/W3013449516","https://openalex.org/W3013818937","https://openalex.org/W3032215537","https://openalex.org/W3082424964","https://openalex.org/W3082849379","https://openalex.org/W3090271579","https://openalex.org/W3094328550","https://openalex.org/W3095064220","https://openalex.org/W3113624456","https://openalex.org/W3114198537","https://openalex.org/W3189373506","https://openalex.org/W4295134715"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W4245750691","https://openalex.org/W2378724343"],"abstract_inverted_index":{"Determining":[0],"the":[1,85,186],"semantic":[2,41],"concepts":[3,55],"of":[4,10,54,73,84,155,190,203],"columns":[5],"in":[6,27,130],"tabular":[7,148],"data":[8,17,76],"is":[9,115],"use":[11],"for":[12,90,147,170,180],"many":[13],"applications":[14],"ranging":[15],"from":[16,47,161],"integration,":[18],"cleaning,":[19],"search":[20],"to":[21,40,66,102,117,132,140],"feature":[22],"engineering":[23],"and":[24,77,138,143,174,177,188],"model":[25],"building":[26],"machine":[28],"learning.":[29],"Several":[30],"prior":[31],"works":[32,88],"have":[33],"proposed":[34],"supervised":[35,62],"learning-based":[36],"or":[37,56],"heuristic-based":[38],"approaches":[39],"type":[42],"annotation.":[43],"These":[44],"techniques":[45,169,179,194],"suffer":[46],"poor":[48],"generalizability":[49],"over":[50,192],"a":[51,96,103,107,153,200],"large":[52,71],"number":[53],"examples.":[57],"Recent":[58],"neural":[59],"network":[60],"based":[61,105],"learning":[63],"methods":[64,87],"generalize":[65],"different":[67],"datasets":[68,198],"but":[69],"require":[70],"amounts":[72,121],"curated":[74],"training":[75],"also":[78,165],"present":[79,94,166],"scalability":[80],"issues.":[81],"Furthermore,":[82],"none":[83],"known":[86],"well":[89],"numerical":[91],"data.":[92,149],"We":[93,164,184],"C2,":[95],"system":[97],"that":[98],"maps":[99],"each":[100],"column":[101],"concept":[104,145],"on":[106,195],"maximum":[108],"likelihood":[109],"estimation":[110],"approach":[111],"through":[112],"ensembles.":[113],"It":[114],"able":[116],"effectively":[118],"utilize":[119,152],"vast":[120],"of,":[122],"albeit":[123],"somewhat":[124],"noisy,":[125],"openly":[126,158],"available":[127,159,193],"table":[128,181],"corpora":[129],"addition":[131],"two":[133],"popular":[134],"knowledge":[135],"graphs":[136],"(Wikidata":[137],"DBpedia),":[139],"perform":[141],"effective":[142],"efficient":[144,167],"annotation":[146],"Specifically,":[150],"we":[151],"collection":[154],"32":[156],"million":[157],"webtables":[160],"several":[162],"sources.":[163],"indexing":[168],"categorical":[171],"string,":[172],"numeric":[173],"mixed-type":[175],"data,":[176],"novel":[178],"context":[182],"utilization.":[183],"demonstrate":[185],"effectiveness":[187],"efficiency":[189],"C2":[191],"9":[196],"real-world":[197],"containing":[199],"wide":[201],"variety":[202],"concepts.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}