{"id":"https://openalex.org/W4387674004","doi":"https://doi.org/10.1007/s13222-023-00457-y","title":"SportsTables: A New Corpus for Semantic Type Detection (Extended Version)","display_name":"SportsTables: A New Corpus for Semantic Type Detection (Extended Version)","publication_year":2023,"publication_date":"2023-10-16","ids":{"openalex":"https://openalex.org/W4387674004","doi":"https://doi.org/10.1007/s13222-023-00457-y"},"language":"en","primary_location":{"id":"doi:10.1007/s13222-023-00457-y","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s13222-023-00457-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-023-00457-y.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s13222-023-00457-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084475721","display_name":"Sven Langenecker","orcid":"https://orcid.org/0009-0002-2809-5331"},"institutions":[{"id":"https://openalex.org/I108806672","display_name":"Baden-Wuerttemberg Cooperative State University","ror":"https://ror.org/02xdzy536","country_code":"DE","type":"education","lineage":["https://openalex.org/I108806672"]},{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sven Langenecker","raw_affiliation_strings":["Duale Hochschule Baden W\u00fcrttemberg Mosbach, Mosbach, Germany","TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Duale Hochschule Baden W\u00fcrttemberg Mosbach, Mosbach, Germany","institution_ids":["https://openalex.org/I108806672"]},{"raw_affiliation_string":"TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003359637","display_name":"Christoph Sturm","orcid":"https://orcid.org/0009-0008-5706-3041"},"institutions":[{"id":"https://openalex.org/I108806672","display_name":"Baden-Wuerttemberg Cooperative State University","ror":"https://ror.org/02xdzy536","country_code":"DE","type":"education","lineage":["https://openalex.org/I108806672"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Sturm","raw_affiliation_strings":["Duale Hochschule Baden W\u00fcrttemberg Mosbach, Mosbach, Germany"],"affiliations":[{"raw_affiliation_string":"Duale Hochschule Baden W\u00fcrttemberg Mosbach, Mosbach, Germany","institution_ids":["https://openalex.org/I108806672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022339518","display_name":"Christian Schalles","orcid":"https://orcid.org/0009-0005-7036-3012"},"institutions":[{"id":"https://openalex.org/I108806672","display_name":"Baden-Wuerttemberg Cooperative State University","ror":"https://ror.org/02xdzy536","country_code":"DE","type":"education","lineage":["https://openalex.org/I108806672"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Schalles","raw_affiliation_strings":["Duale Hochschule Baden W\u00fcrttemberg Mosbach, Mosbach, Germany"],"affiliations":[{"raw_affiliation_string":"Duale Hochschule Baden W\u00fcrttemberg Mosbach, Mosbach, Germany","institution_ids":["https://openalex.org/I108806672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073504200","display_name":"Carsten Binnig","orcid":"https://orcid.org/0000-0002-2744-7836"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carsten Binnig","raw_affiliation_strings":["DFKI Darmstadt, Darmstadt, Germany","TU Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"DFKI Darmstadt, Darmstadt, Germany","institution_ids":[]},{"raw_affiliation_string":"TU Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084475721"],"corresponding_institution_ids":["https://openalex.org/I108806672","https://openalex.org/I31512782"],"apc_list":{"value":2380,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2380,"currency":"EUR","value_usd":2890},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13486969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"3","first_page":"189","last_page":"197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.994700014591217,"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":0.7778950929641724},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5812364816665649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5383826494216919},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5350547432899475},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.528670072555542},{"id":"https://openalex.org/keywords/type","display_name":"Type (biology)","score":0.5164070725440979},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.4669308066368103},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.45598721504211426},{"id":"https://openalex.org/keywords/approx","display_name":"Approx","score":0.42241108417510986},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.144332617521286},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.0706000030040741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778950929641724},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5812364816665649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5383826494216919},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5350547432899475},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.528670072555542},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.5164070725440979},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.4669308066368103},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.45598721504211426},{"id":"https://openalex.org/C2777894999","wikidata":"https://www.wikidata.org/wiki/Q4781758","display_name":"Approx","level":2,"score":0.42241108417510986},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.144332617521286},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0706000030040741},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s13222-023-00457-y","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s13222-023-00457-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-023-00457-y.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:153393","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/view/person/Langenecker=3ASven=3A=3A.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"}],"best_oa_location":{"id":"doi:10.1007/s13222-023-00457-y","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s13222-023-00457-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s13222-023-00457-y.pdf","source":{"id":"https://openalex.org/S73012565","display_name":"Datenbank-Spektrum","issn_l":"1610-1995","issn":["1610-1995","1618-2162"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Datenbank-Spektrum","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2843248846","display_name":null,"funder_award_id":"02P20A064","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G2991786998","display_name":null,"funder_award_id":"02L19C150","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320323384","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387674004.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W1995875735","https://openalex.org/W2108223890","https://openalex.org/W2119828234","https://openalex.org/W2196674927","https://openalex.org/W2398606196","https://openalex.org/W2522705507","https://openalex.org/W2537262135","https://openalex.org/W2941366772","https://openalex.org/W2951621897","https://openalex.org/W2963341956","https://openalex.org/W3008479101","https://openalex.org/W3082424964","https://openalex.org/W3145728363","https://openalex.org/W3208380906","https://openalex.org/W3208506743","https://openalex.org/W4205922070","https://openalex.org/W4393445846","https://openalex.org/W4393496336","https://openalex.org/W4393880248","https://openalex.org/W4393921590","https://openalex.org/W4394024816","https://openalex.org/W6906836667"],"related_works":["https://openalex.org/W2277483927","https://openalex.org/W1867383269","https://openalex.org/W4394360958","https://openalex.org/W399943172","https://openalex.org/W2181722423","https://openalex.org/W2948670949","https://openalex.org/W4288047943","https://openalex.org/W2300902614","https://openalex.org/W2347222412","https://openalex.org/W3123448197"],"abstract_inverted_index":{"Abstract":[0],"Table":[1],"corpora":[2,37],"such":[3],"as":[4],"VizNet":[5],"or":[6],"TURL":[7],"which":[8,51,106],"contain":[9,44],"annotated":[10],"semantic":[11,27,102,139,155],"types":[12,156],"per":[13],"column":[14],"are":[15,52],"important":[16],"to":[17,100],"build":[18],"machine":[19],"learning":[20],"models":[21,105],"for":[22,138,157],"the":[23,81,127,147],"task":[24],"of":[25,48,73,125,129],"automatic":[26],"type":[28,103,140],"detection.":[29],"However,":[30],"there":[31],"is":[32],"a":[33,45,64,69],"huge":[34,46],"discrepancy":[35],"between":[36],"and":[38,159],"real-world":[39,84],"data":[40,50,85],"lakes":[41],"since":[42],"they":[43],"fraction":[47],"numerical":[49,74,95,160],"not":[53],"present":[54],"in":[55,59,83,120,153],"existing":[56,77,101],"corpora.":[57,78],"Hence,":[58],"this":[60,116,121],"paper,":[61],"we":[62,118],"introduce":[63],"new":[65,98,144],"corpus":[66,88],"that":[67],"contains":[68],"much":[70],"higher":[71],"proportion":[72],"columns":[75,111],"than":[76],"To":[79,114],"reflect":[80],"distribution":[82],"lakes,":[86],"our":[87,143],"SportsTables":[89],"has":[90],"on":[91,142],"average":[92],"approx.":[93],"86%":[94],"columns,":[96],"posing":[97],"challenges":[99],"detection":[104,141],"have":[107],"mainly":[108],"targeted":[109],"non-numerical":[110],"so":[112],"far.":[113],"demonstrate":[115,149],"effect,":[117],"show":[119],"extended":[122],"version":[123],"paper":[124],"[18]":[126],"results":[128,148],"an":[130],"extensive":[131],"study":[132],"using":[133],"four":[134],"different":[135],"state-of-the-art":[136],"approaches":[137],"corpus.":[145],"Overall,":[146],"significant":[150],"performance":[151],"differences":[152],"predicting":[154],"textual":[158],"data.":[161]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
