{"id":"https://openalex.org/W2602288119","doi":"https://doi.org/10.1109/tcyb.2017.2680466","title":"Active Learning of Regular Expressions for Entity Extraction","display_name":"Active Learning of Regular Expressions for Entity Extraction","publication_year":2017,"publication_date":"2017-03-25","ids":{"openalex":"https://openalex.org/W2602288119","doi":"https://doi.org/10.1109/tcyb.2017.2680466","mag":"2602288119","pmid":"https://pubmed.ncbi.nlm.nih.gov/28358694"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2017.2680466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2017.2680466","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ieeexplore.ieee.org/document/7886274/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019727872","display_name":"Alberto Bartoli","orcid":"https://orcid.org/0000-0003-4132-416X"},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Bartoli","raw_affiliation_strings":["Department of Engineering and Architecture, University of Trieste, Trieste, Italy"],"raw_orcid":"https://orcid.org/0000-0003-4132-416X","affiliations":[{"raw_affiliation_string":"Department of Engineering and Architecture, University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031604878","display_name":"Andrea De Lorenzo","orcid":"https://orcid.org/0000-0002-7628-7672"},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea De Lorenzo","raw_affiliation_strings":["Department of Engineering and Architecture, University of Trieste, Trieste, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering and Architecture, University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074055647","display_name":"Eric Medvet","orcid":"https://orcid.org/0000-0001-5652-2113"},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Eric Medvet","raw_affiliation_strings":["Department of Engineering and Architecture, University of Trieste, Trieste, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering and Architecture, University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024227702","display_name":"Fabiano Tarlao","orcid":null},"institutions":[{"id":"https://openalex.org/I142444530","display_name":"University of Trieste","ror":"https://ror.org/02n742c10","country_code":"IT","type":"education","lineage":["https://openalex.org/I142444530"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabiano Tarlao","raw_affiliation_strings":["Department of Engineering and Architecture, University of Trieste, Trieste, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering and Architecture, University of Trieste, Trieste, Italy","institution_ids":["https://openalex.org/I142444530"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142444530"],"apc_list":null,"apc_paid":null,"fwci":3.9863,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.94943416,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"48","issue":"3","first_page":"1067","last_page":"1080"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9991999864578247,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9991999864578247,"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":0.9923999905586243,"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":0.9810000061988831,"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":0.8660827875137329},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.8276055455207825},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6717862486839294},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.6026991009712219},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5789073705673218},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5777422189712524},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5679155588150024},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.5334174036979675},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4379643499851227},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4128165543079376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3786839246749878},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1044650673866272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8660827875137329},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.8276055455207825},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6717862486839294},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.6026991009712219},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5789073705673218},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5777422189712524},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5679155588150024},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.5334174036979675},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4379643499851227},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4128165543079376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3786839246749878},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1044650673866272},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcyb.2017.2680466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2017.2680466","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:28358694","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28358694","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null},{"id":"pmh:oai:arts.units.it:11368/2898072","is_oa":true,"landing_page_url":"http://ieeexplore.ieee.org/document/7886274/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400480","display_name":"ArTS Archivio della ricerca di Trieste (University of Trieste https://www.units.it/)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142444530","host_organization_name":"University of Trieste","host_organization_lineage":["https://openalex.org/I142444530"],"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":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arts.units.it:11368/2898072","is_oa":true,"landing_page_url":"http://ieeexplore.ieee.org/document/7886274/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400480","display_name":"ArTS Archivio della ricerca di Trieste (University of Trieste https://www.units.it/)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142444530","host_organization_name":"University of Trieste","host_organization_lineage":["https://openalex.org/I142444530"],"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":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W35034236","https://openalex.org/W72959484","https://openalex.org/W627888170","https://openalex.org/W1499578805","https://openalex.org/W1568705965","https://openalex.org/W1576818901","https://openalex.org/W1580375566","https://openalex.org/W1671614046","https://openalex.org/W1976035027","https://openalex.org/W1978982221","https://openalex.org/W1979800980","https://openalex.org/W1982804187","https://openalex.org/W1987538593","https://openalex.org/W1991234467","https://openalex.org/W1991347287","https://openalex.org/W2018770010","https://openalex.org/W2023437071","https://openalex.org/W2026213144","https://openalex.org/W2027825959","https://openalex.org/W2038941723","https://openalex.org/W2039532210","https://openalex.org/W2053606499","https://openalex.org/W2058919894","https://openalex.org/W2059383863","https://openalex.org/W2068541969","https://openalex.org/W2071305045","https://openalex.org/W2072998720","https://openalex.org/W2077482713","https://openalex.org/W2078887230","https://openalex.org/W2080021732","https://openalex.org/W2085989833","https://openalex.org/W2095537056","https://openalex.org/W2098203240","https://openalex.org/W2102162869","https://openalex.org/W2106950427","https://openalex.org/W2117847370","https://openalex.org/W2124651849","https://openalex.org/W2132667707","https://openalex.org/W2137795521","https://openalex.org/W2138517257","https://openalex.org/W2139709458","https://openalex.org/W2144951274","https://openalex.org/W2146105230","https://openalex.org/W2161816739","https://openalex.org/W2171972164","https://openalex.org/W2275294428","https://openalex.org/W2484789285","https://openalex.org/W2735531870","https://openalex.org/W2903158431","https://openalex.org/W2951911250","https://openalex.org/W4245220551","https://openalex.org/W4252861488","https://openalex.org/W4256244129","https://openalex.org/W6601396651","https://openalex.org/W6629913273","https://openalex.org/W6655195918","https://openalex.org/W6675206559","https://openalex.org/W6680113041","https://openalex.org/W6680770092","https://openalex.org/W6756615331"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2358755282","https://openalex.org/W2352448290","https://openalex.org/W2380820513"],"abstract_inverted_index":{"We":[0,119,171],"consider":[1],"the":[2,10,19,43,53,67,71,86,89,92,96,101,110,116,143,148,157,190],"automatic":[3],"synthesis":[4],"of":[5,12,18,46,133,140,150,159,165,180,189,209],"an":[6,23,60],"entity":[7,166],"extractor,":[8],"in":[9,22,112,175,194,207],"form":[11,132],"a":[13,29,47,131,138,178,186,218],"regular":[14],"expression,":[15],"from":[16,168],"examples":[17],"desired":[20,76],"extractions":[21],"unstructured":[24,169],"text":[25,98],"stream.":[26],"This":[27],"is":[28],"long-standing":[30],"problem":[31],"for":[32,99],"which":[33,40],"many":[34],"different":[35],"approaches":[36],"have":[37],"been":[38],"proposed,":[39],"all":[41],"require":[42],"preliminary":[44],"construction":[45],"large":[48],"dataset":[49],"fully":[50],"annotated":[51,212],"by":[52,85],"user.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"propose":[59],"active":[61,160],"learning":[62,90,161],"approach":[63],"aimed":[64],"at":[65],"minimizing":[66],"user":[68,72,111,191],"annotation":[69],"effort:":[70],"annotates":[73],"only":[74],"one":[75],"extraction":[77,82,104,167],"and":[78,127,164,183,214],"then":[79],"merely":[80],"answers":[81],"queries":[83,129],"generated":[84],"system.":[87],"During":[88],"process,":[91],"system":[93,152],"digs":[94],"into":[95],"input":[97],"selecting":[100],"most":[102],"appropriate":[103],"query":[105],"to":[106,109,114,156],"be":[107],"submitted":[108],"order":[113],"improve":[115],"current":[117],"extractor.":[118],"construct":[120],"candidate":[121,145],"solutions":[122],"with":[123,130,162,204],"genetic":[124],"programming":[125],"(GP)":[126],"select":[128],"querying-by-committee,":[134],"i.e.,":[135],"based":[136,184],"on":[137,177,185],"measure":[139],"disagreement":[141],"within":[142],"best":[144],"solutions.":[146],"All":[147],"components":[149],"our":[151,173],"are":[153],"carefully":[154],"tailored":[155],"peculiarities":[158],"GP":[163],"text.":[170],"evaluate":[172],"proposal":[174],"depth,":[176],"number":[179],"challenging":[181],"datasets":[182],"realistic":[187],"estimate":[188],"effort":[192],"involved":[193],"answering":[195],"each":[196],"single":[197],"query.":[198],"The":[199],"results":[200],"demonstrate":[201],"high":[202],"accuracy":[203],"significant":[205],"savings":[206],"terms":[208],"computational":[210],"effort,":[211],"characters,":[213],"execution":[215],"time":[216],"over":[217],"state-of-the-art":[219],"baseline.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}