{"id":"https://openalex.org/W2963265283","doi":"https://doi.org/10.1145/3196959.3196968","title":"Document Spanners for Extracting Incomplete Information","display_name":"Document Spanners for Extracting Incomplete Information","publication_year":2018,"publication_date":"2018-05-15","ids":{"openalex":"https://openalex.org/W2963265283","doi":"https://doi.org/10.1145/3196959.3196968","mag":"2963265283"},"language":"en","primary_location":{"id":"doi:10.1145/3196959.3196968","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3196959.3196968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","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/A5068437513","display_name":"Francisco Maturana","orcid":"https://orcid.org/0000-0002-7532-8399"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Francisco Maturana","raw_affiliation_strings":["Carnegie Mellon University, Pittsburg, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburg, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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 Catolica de Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Pontificia Universidad Catolica de Chile, Santiago, 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 Vrgoc","raw_affiliation_strings":["Pontificia Universidad Catolica de Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Pontificia Universidad Catolica de Chile, Santiago, Chile","institution_ids":["https://openalex.org/I162148367"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068437513"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":3.5835,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94404975,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"125","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9986000061035156,"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":0.9986000061035156,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8164799213409424},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.7070188522338867},{"id":"https://openalex.org/keywords/satisfiability","display_name":"Satisfiability","score":0.6902867555618286},{"id":"https://openalex.org/keywords/containment","display_name":"Containment (computer programming)","score":0.6362564563751221},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6230765581130981},{"id":"https://openalex.org/keywords/expressive-power","display_name":"Expressive power","score":0.5779811143875122},{"id":"https://openalex.org/keywords/enumeration","display_name":"Enumeration","score":0.5080645084381104},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.41735172271728516},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35533982515335083},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.353430837392807},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3516719341278076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3249838948249817},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10239613056182861}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8164799213409424},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.7070188522338867},{"id":"https://openalex.org/C168773769","wikidata":"https://www.wikidata.org/wiki/Q1350299","display_name":"Satisfiability","level":2,"score":0.6902867555618286},{"id":"https://openalex.org/C2777019822","wikidata":"https://www.wikidata.org/wiki/Q390066","display_name":"Containment (computer programming)","level":2,"score":0.6362564563751221},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6230765581130981},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.5779811143875122},{"id":"https://openalex.org/C156340839","wikidata":"https://www.wikidata.org/wiki/Q2704791","display_name":"Enumeration","level":2,"score":0.5080645084381104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41735172271728516},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35533982515335083},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.353430837392807},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3516719341278076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3249838948249817},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10239613056182861},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3196959.3196968","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3196959.3196968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G1550605022","display_name":null,"funder_award_id":"11160383, 11150653","funder_id":"https://openalex.org/F4320338073","funder_display_name":"Fondo Nacional de Desarrollo Cient\u00edfico y Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320338073","display_name":"Fondo Nacional de Desarrollo Cient\u00edfico y Tecnol\u00f3gico","ror":"https://ror.org/02ap3w078"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1558832481","https://openalex.org/W1570425181","https://openalex.org/W1607983314","https://openalex.org/W1992673035","https://openalex.org/W1998084650","https://openalex.org/W2002089154","https://openalex.org/W2007940874","https://openalex.org/W2039242856","https://openalex.org/W2110367654","https://openalex.org/W2116548113","https://openalex.org/W2131785201","https://openalex.org/W2141456009","https://openalex.org/W2144416276","https://openalex.org/W2162340487","https://openalex.org/W2490706771","https://openalex.org/W2498523297","https://openalex.org/W2952981883","https://openalex.org/W3195236188","https://openalex.org/W4206031975"],"related_works":["https://openalex.org/W108845024","https://openalex.org/W4300125793","https://openalex.org/W2578985712","https://openalex.org/W2406961474","https://openalex.org/W2143566611","https://openalex.org/W3083527377","https://openalex.org/W2743317844","https://openalex.org/W27822467","https://openalex.org/W2952866644","https://openalex.org/W2885565263"],"abstract_inverted_index":{"Rule-based":[0],"information":[1,25,62],"extraction":[2,26,63,95],"has":[3],"lately":[4],"received":[5],"a":[6],"fair":[7],"amount":[8],"of":[9,50,91,121,129],"attention":[10],"from":[11],"the":[12,20,56,66,89,108,134],"database":[13],"community,":[14],"with":[15,32,65,76,107],"several":[16],"languages":[17,64],"appearing":[18],"in":[19,119],"last":[21],"few":[22],"years.":[23],"Although":[24],"systems":[27],"are":[28,41],"intended":[29],"to":[30,43,60,68,74,110],"deal":[31],"semistructured":[33],"data,":[34,113],"all":[35],"language":[36],"proposals":[37],"introduced":[38],"so":[39],"far":[40],"designed":[42],"output":[44],"relations,":[45],"thus":[46,71],"making":[47],"them":[48,106],"incapable":[49],"handling":[51],"incomplete":[52,112],"information.":[53,103],"To":[54],"remedy":[55],"situation,":[57],"we":[58,87],"propose":[59],"extend":[61,105],"ability":[67,109],"use":[69],"mappings,":[70],"allowing":[72],"us":[73],"work":[75],"documents":[77],"which":[78],"have":[79],"missing":[80],"or":[81],"optional":[82],"parts.":[83],"Using":[84],"this":[85],"approach,":[86],"simplify":[88],"semantics":[90],"regex":[92],"formulas":[93],"and":[94,114,142],"rules,":[96],"two":[97],"previously":[98],"defined":[99],"methods":[100],"for":[101],"extracting":[102],"We":[104,124],"handle":[111],"study":[115,126],"how":[116],"they":[117],"compare":[118],"terms":[120],"expressive":[122],"power.":[123],"also":[125],"computational":[127],"properties":[128],"these":[130],"languages,":[131],"focusing":[132],"on":[133],"query":[135],"enumeration":[136],"problem,":[137],"as":[138,140],"well":[139],"satisfiability":[141],"containment.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}