{"id":"https://openalex.org/W2498523297","doi":"https://doi.org/10.14778/2983200.2983204","title":"A framework for annotating CSV-like data","display_name":"A framework for annotating CSV-like data","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2498523297","doi":"https://doi.org/10.14778/2983200.2983204","mag":"2498523297"},"language":"en","primary_location":{"id":"doi:10.14778/2983200.2983204","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2983200.2983204","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5011691423","display_name":"Marcelo Arenas","orcid":"https://orcid.org/0000-0003-3678-1868"},"institutions":[{"id":"https://openalex.org/I162148367","display_name":"Pontificia Universidad Cat\u00f3lica de Chile","ror":"https://ror.org/04teye511","country_code":"CL","type":"education","lineage":["https://openalex.org/I162148367"]}],"countries":["CL"],"is_corresponding":true,"raw_author_name":"Marcelo Arenas","raw_affiliation_strings":["Pontificia Universidad Cat\u00f3lica de Chile"],"affiliations":[{"raw_affiliation_string":"Pontificia Universidad Cat\u00f3lica de Chile","institution_ids":["https://openalex.org/I162148367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068437513","display_name":"Francisco Maturana","orcid":"https://orcid.org/0000-0002-7532-8399"},"institutions":[{"id":"https://openalex.org/I162148367","display_name":"Pontificia Universidad Cat\u00f3lica de Chile","ror":"https://ror.org/04teye511","country_code":"CL","type":"education","lineage":["https://openalex.org/I162148367"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Francisco Maturana","raw_affiliation_strings":["Pontificia Universidad Cat\u00f3lica de Chile"],"affiliations":[{"raw_affiliation_string":"Pontificia Universidad Cat\u00f3lica de Chile","institution_ids":["https://openalex.org/I162148367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083030983","display_name":"Cristian Riveros","orcid":"https://orcid.org/0000-0003-0832-116X"},"institutions":[{"id":"https://openalex.org/I162148367","display_name":"Pontificia Universidad Cat\u00f3lica de Chile","ror":"https://ror.org/04teye511","country_code":"CL","type":"education","lineage":["https://openalex.org/I162148367"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Cristian Riveros","raw_affiliation_strings":["Pontificia Universidad Cat\u00f3lica de Chile"],"affiliations":[{"raw_affiliation_string":"Pontificia Universidad Cat\u00f3lica de Chile","institution_ids":["https://openalex.org/I162148367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065838322","display_name":"Domagoj Vrgo\u010d","orcid":"https://orcid.org/0000-0001-5854-2652"},"institutions":[{"id":"https://openalex.org/I162148367","display_name":"Pontificia Universidad Cat\u00f3lica de Chile","ror":"https://ror.org/04teye511","country_code":"CL","type":"education","lineage":["https://openalex.org/I162148367"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Domagoj Vrgo\u010d","raw_affiliation_strings":["Pontificia Universidad Cat\u00f3lica de Chile"],"affiliations":[{"raw_affiliation_string":"Pontificia Universidad Cat\u00f3lica de Chile","institution_ids":["https://openalex.org/I162148367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011691423"],"corresponding_institution_ids":["https://openalex.org/I162148367"],"apc_list":null,"apc_paid":null,"fwci":2.9993,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92784031,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":"11","first_page":"876","last_page":"887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9980999827384949,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9980999827384949,"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":0.9950000047683716,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9939000010490417,"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":0.8665593266487122},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7331156730651855},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6019027829170227},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5161193609237671},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4358142912387848},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.37434321641921997},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35872307419776917},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3584611713886261},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3287697434425354},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09239214658737183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8665593266487122},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7331156730651855},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6019027829170227},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5161193609237671},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4358142912387848},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37434321641921997},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35872307419776917},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3584611713886261},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3287697434425354},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09239214658737183},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2983200.2983204","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2983200.2983204","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1487895014","https://openalex.org/W1558832481","https://openalex.org/W1689425719","https://openalex.org/W1969965298","https://openalex.org/W1976055110","https://openalex.org/W2035266017","https://openalex.org/W2067308467","https://openalex.org/W2099964107","https://openalex.org/W2111465715","https://openalex.org/W2141456009","https://openalex.org/W2144416276","https://openalex.org/W2156919279","https://openalex.org/W2274383117","https://openalex.org/W6628956856","https://openalex.org/W6694180371"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2501188010","https://openalex.org/W4299935056","https://openalex.org/W2768810474","https://openalex.org/W599624254"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,110],"propose":[4],"a":[5,48,67,106,118],"simple":[6],"and":[7,16,86,100,125],"expressive":[8],"framework":[9,21,46,85,116],"for":[10,58],"adding":[11],"metadata":[12],"to":[13,35,73,97],"CSV":[14],"documents":[15],"their":[17],"noisy":[18],"variants.":[19],"The":[20,42],"is":[22,47],"based":[23,50],"on":[24,51],"annotating":[25],"parts":[26],"of":[27,44,69,82,108,114,121],"the":[28,40,75,79],"document":[29],"that":[30,55,92,127],"can":[31,129],"be":[32,130],"later":[33],"used":[34,57,132],"read,":[36],"query,":[37],"or":[38],"exchange":[39],"data.":[41,60,76],"core":[43],"our":[45,84,115],"language":[49],"extended":[52],"regular":[53],"expressions":[54,62],"are":[56,63],"selecting":[59],"These":[61],"then":[64],"combined":[65],"using":[66],"set":[68],"rules":[70],"in":[71,94,102,133],"order":[72],"annotate":[74],"We":[77],"study":[78],"computational":[80],"complexity":[81],"implementing":[83],"present":[87],"an":[88,112],"efficient":[89],"evaluation":[90],"algorithm":[91],"runs":[93],"time":[95],"proportional":[96],"its":[98,103],"output":[99],"linear":[101],"input.":[104],"As":[105],"proof":[107],"concept,":[109],"test":[111],"implementation":[113],"against":[117],"large":[119],"number":[120],"real":[122],"world":[123],"datasets":[124],"show":[126],"it":[128],"efficiently":[131],"practice.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
