{"id":"https://openalex.org/W2038941723","doi":"https://doi.org/10.1145/2063576.2063763","title":"Enabling information extraction by inference of regular expressions from sample entities","display_name":"Enabling information extraction by inference of regular expressions from sample entities","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W2038941723","doi":"https://doi.org/10.1145/2063576.2063763","mag":"2038941723"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063763","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3438493","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026608646","display_name":"Falk Brauer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135152","display_name":"Roland Ernst Stiftung","ror":"https://ror.org/03m629g08","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210135152"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Falk Brauer","raw_affiliation_strings":["SAP AG, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"SAP AG, Dresden, Germany","institution_ids":["https://openalex.org/I4210135152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075504983","display_name":"Robert Rieger","orcid":"https://orcid.org/0000-0002-4436-0804"},"institutions":[{"id":"https://openalex.org/I4210135152","display_name":"Roland Ernst Stiftung","ror":"https://ror.org/03m629g08","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210135152"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert Rieger","raw_affiliation_strings":["SAP AG, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"SAP AG, Dresden, Germany","institution_ids":["https://openalex.org/I4210135152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056919803","display_name":"Adrian Mocan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135152","display_name":"Roland Ernst Stiftung","ror":"https://ror.org/03m629g08","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210135152"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adrian Mocan","raw_affiliation_strings":["SAP AG, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"SAP AG, Dresden, Germany","institution_ids":["https://openalex.org/I4210135152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045754291","display_name":"Wojciech M. Barczy\u0144ski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135152","display_name":"Roland Ernst Stiftung","ror":"https://ror.org/03m629g08","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210135152"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wojciech M. Barczynski","raw_affiliation_strings":["SAP AG, Dresden, Germany"],"affiliations":[{"raw_affiliation_string":"SAP AG, Dresden, Germany","institution_ids":["https://openalex.org/I4210135152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026608646"],"corresponding_institution_ids":["https://openalex.org/I4210135152"],"apc_list":null,"apc_paid":null,"fwci":7.3894,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.96720821,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1285","last_page":"1294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/regular-expression","display_name":"Regular expression","score":0.8508687615394592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.806972861289978},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6208131313323975},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5498263835906982},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.528601884841919},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5241753458976746},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5058135986328125},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4887392520904541},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47741496562957764},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.45754286646842957},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4560955762863159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4441717863082886},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4289625883102417},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4255581498146057},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.41019272804260254},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3857506215572357},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1562064290046692},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11344635486602783}],"concepts":[{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.8508687615394592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806972861289978},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6208131313323975},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5498263835906982},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.528601884841919},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5241753458976746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5058135986328125},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4887392520904541},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47741496562957764},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.45754286646842957},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4560955762863159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4441717863082886},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4289625883102417},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4255581498146057},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.41019272804260254},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3857506215572357},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1562064290046692},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11344635486602783},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2063576.2063763","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:3438493","is_oa":true,"landing_page_url":"https://zenodo.org/record/3438493","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3438493","is_oa":true,"landing_page_url":"https://zenodo.org/record/3438493","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W108998739","https://openalex.org/W263614502","https://openalex.org/W1499578805","https://openalex.org/W1585280831","https://openalex.org/W1585388492","https://openalex.org/W1967053016","https://openalex.org/W2063985934","https://openalex.org/W2080666934","https://openalex.org/W2106895292","https://openalex.org/W2106950427","https://openalex.org/W2108126629","https://openalex.org/W2111284344","https://openalex.org/W2111727122","https://openalex.org/W2116493296","https://openalex.org/W2147880316","https://openalex.org/W2162340487","https://openalex.org/W2163915185","https://openalex.org/W2163980860","https://openalex.org/W2421105961","https://openalex.org/W2913389685","https://openalex.org/W4248809068","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2164820101","https://openalex.org/W2367919820","https://openalex.org/W2004087619","https://openalex.org/W4321472216","https://openalex.org/W2557094866","https://openalex.org/W72959484","https://openalex.org/W2469016277","https://openalex.org/W2362196274","https://openalex.org/W2757101400","https://openalex.org/W1982302668"],"abstract_inverted_index":{"Regular":[0],"expressions":[1,39,67,107],"are":[2],"the":[3,34,145],"dominant":[4],"technique":[5],"to":[6,149],"extract":[7],"business":[8],"relevant":[9],"entities":[10],"(e.g.,":[11,20,85,92],"invoice":[12],"numbers":[13],"or":[14,89],"product":[15,87],"names)":[16],"from":[17,68,82],"text":[18],"data":[19],"invoices),":[21],"since":[22],"these":[23],"entity":[24,129],"types":[25],"often":[26],"follow":[27],"a":[28,42,48,69,86,116,123,151],"strict":[29],"underlying":[30],"syntactical":[31],"pattern.":[32],"However,":[33],"manual":[35,50],"construction":[36],"of":[37,71,98,131],"regular":[38,66,106,152],"that":[40,63,102,108,126],"guarantee":[41],"high":[43],"recall":[44],"and":[45,52,113,137,143],"precision":[46],"is":[47,101,120],"tedious":[49],"task":[51],"requires":[53],"expert":[54],"knowledge.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59],"propose":[60],"an":[61],"approach":[62,100],"automatically":[64],"infers":[65],"set":[70],"(positive)":[72],"sample":[73],"entities,":[74],"which":[75],"in":[76],"turn":[77],"can":[78,109],"be":[79,110],"derived":[80],"either":[81],"enterprise":[83],"databases":[84],"catalog)":[88],"annotated":[90],"documents":[91],"historical":[93],"invoices).":[94],"The":[95,118],"main":[96],"innovation":[97],"our":[99],"it":[103],"learns":[104],"effective":[105],"easily":[111],"interpreted":[112],"modified":[114],"by":[115,122],"user.":[117],"effectiveness":[119],"obtained":[121],"novel":[124],"method":[125],"weights":[127],"dependent":[128],"features":[130],"different":[132],"granularity":[133],"(i.e.":[134],"on":[135],"character":[136],"token":[138],"level)":[139],"against":[140],"each":[141],"other":[142],"selects":[144],"most":[146],"suitable":[147],"ones":[148],"form":[150],"expression.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}