{"id":"https://openalex.org/W2046441607","doi":"https://doi.org/10.1145/2452376.2452457","title":"Entity discovery and annotation in tables","display_name":"Entity discovery and annotation in tables","publication_year":2013,"publication_date":"2013-03-18","ids":{"openalex":"https://openalex.org/W2046441607","doi":"https://doi.org/10.1145/2452376.2452457","mag":"2046441607"},"language":"en","primary_location":{"id":"doi:10.1145/2452376.2452457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2452376.2452457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Extending Database Technology","raw_type":"proceedings-article"},"type":"conference-paper","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/A5028238165","display_name":"Gianluca Quercini","orcid":"https://orcid.org/0000-0001-9195-1618"},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gianluca Quercini","raw_affiliation_strings":["Universit\u00e9 Paris-Sud XI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Sud XI","institution_ids":["https://openalex.org/I102197404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082680613","display_name":"Chantal Reynaud","orcid":null},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chantal Reynaud","raw_affiliation_strings":["Universit\u00e9 Paris-Sud XI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Sud XI","institution_ids":["https://openalex.org/I102197404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102197404"],"apc_list":null,"apc_paid":null,"fwci":6.1996,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96813187,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"693","last_page":"704"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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":0.8161022663116455},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.729269802570343},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6881557703018188},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.666672945022583},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6037643551826477},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5935098528862},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5114256739616394},{"id":"https://openalex.org/keywords/semi-structured-data","display_name":"Semi-structured data","score":0.431900292634964},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4275829792022705},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3636014461517334},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.3506719470024109},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34483030438423157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2602715790271759},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15440163016319275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8161022663116455},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.729269802570343},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6881557703018188},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.666672945022583},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6037643551826477},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5935098528862},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5114256739616394},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.431900292634964},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4275829792022705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3636014461517334},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3506719470024109},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34483030438423157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2602715790271759},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15440163016319275},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/2452376.2452457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2452376.2452457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Extending Database Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.9727","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.9727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.edbt.org/Proceedings/2013-Genova/papers/edbt/a62-quercini.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.949.5683","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.949.5683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/hal-00832639/document/","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00832639v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-00832639","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EDBT: Inernational Conference on Extending Database Technology, Mar 2013, Genoa, Italy","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1495062271","https://openalex.org/W1509330973","https://openalex.org/W1546430096","https://openalex.org/W1562673218","https://openalex.org/W1595020351","https://openalex.org/W1774363252","https://openalex.org/W1981388173","https://openalex.org/W2020740057","https://openalex.org/W2022166150","https://openalex.org/W2026937586","https://openalex.org/W2087619920","https://openalex.org/W2092364718","https://openalex.org/W2093189534","https://openalex.org/W2096820050","https://openalex.org/W2104586313","https://openalex.org/W2108223890","https://openalex.org/W2109943925","https://openalex.org/W2111869785","https://openalex.org/W2136134253","https://openalex.org/W2138605095","https://openalex.org/W2151846280","https://openalex.org/W2153225416","https://openalex.org/W2741225114"],"related_works":["https://openalex.org/W2163934370","https://openalex.org/W2016355461","https://openalex.org/W2386938185","https://openalex.org/W2068844411","https://openalex.org/W1986386500","https://openalex.org/W2098516643","https://openalex.org/W2576225315","https://openalex.org/W2793958305","https://openalex.org/W2793744252","https://openalex.org/W1516746680"],"abstract_inverted_index":{"The":[0,40],"Web":[1],"is":[2,43],"rich":[3],"of":[4,18,31,34,49],"tables":[5,25],"(e.g.,":[6],"HTML":[7],"tables,":[8],"spreadsheets,":[9],"Google":[10],"Fusion":[11],"Tables)":[12],"that":[13,72],"host":[14],"a":[15,58],"considerable":[16],"wealth":[17],"high-quality":[19],"relational":[20],"data.":[21],"Unlike":[22],"unstructured":[23],"texts,":[24],"usually":[26,44],"favour":[27],"the":[28,47,50,63,70],"automatic":[29],"extraction":[30,42],"data":[32,41],"because":[33],"their":[35],"regular":[36],"structure":[37],"and":[38,69],"properties.":[39],"complemented":[45],"by":[46,56],"annotation":[48],"table,":[51],"which":[52],"determines":[53],"its":[54],"semantics":[55],"identifying":[57],"type":[59],"for":[60],"each":[61,75],"column,":[62],"relations":[64],"between":[65],"columns,":[66],"if":[67],"any,":[68],"entities":[71],"occur":[73],"in":[74],"cell.":[76]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}