{"id":"https://openalex.org/W2076977343","doi":"https://doi.org/10.1017/s135132490400333x","title":"LearningPinocchio: adaptive information extraction for real world applications","display_name":"LearningPinocchio: adaptive information extraction for real world applications","publication_year":2004,"publication_date":"2004-05-13","ids":{"openalex":"https://openalex.org/W2076977343","doi":"https://doi.org/10.1017/s135132490400333x","mag":"2076977343"},"language":"en","primary_location":{"id":"doi:10.1017/s135132490400333x","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s135132490400333x","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","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/A5052671966","display_name":"Fabio Ciravegna","orcid":"https://orcid.org/0000-0001-5817-4810"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"F. CIRAVEGNA","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, S1 4DP Sheffield, UK e-mail:","Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, S1 4DP Sheffield, UK e-mail: F.Ciravegna@dcs.shef.ac.uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, S1 4DP Sheffield, UK e-mail:","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, S1 4DP Sheffield, UK e-mail: F.Ciravegna@dcs.shef.ac.uk","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073069826","display_name":"Alberto Lavelli","orcid":"https://orcid.org/0000-0002-7175-6804"},"institutions":[{"id":"https://openalex.org/I4210097842","display_name":"Istituto Centrale per la Ricerca Scientifica e Tecnologica Applicata al Mare","ror":"https://ror.org/014cycx13","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210097842"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"A. LAVELLI","raw_affiliation_strings":["ITC-irst Centro per la Ricerca Scientifica e Tecnologica, via Sommarive 18, 38050 Povo (TN), Italy e-mail:","ITC-irst Centro per la Ricerca Scientifica e Tecnologica, via Sommarive 18, 38050 Povo (TN), Italy e-mail: [email\u00a0protected]#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITC-irst Centro per la Ricerca Scientifica e Tecnologica, via Sommarive 18, 38050 Povo (TN), Italy e-mail:","institution_ids":["https://openalex.org/I4210097842"]},{"raw_affiliation_string":"ITC-irst Centro per la Ricerca Scientifica e Tecnologica, via Sommarive 18, 38050 Povo (TN), Italy e-mail: [email\u00a0protected]#TAB#","institution_ids":["https://openalex.org/I4210097842"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0239,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94124541,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":"2","first_page":"145","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T10260","display_name":"Software Engineering Research","score":0.989300012588501,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8905227780342102},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.8502999544143677},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6527850031852722},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.44737541675567627},{"id":"https://openalex.org/keywords/frontier","display_name":"Frontier","score":0.4150789976119995},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3969394564628601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3535979986190796},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.33881425857543945},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09096977114677429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8905227780342102},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8502999544143677},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6527850031852722},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.44737541675567627},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.4150789976119995},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3969394564628601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3535979986190796},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.33881425857543945},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09096977114677429},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s135132490400333x","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s135132490400333x","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.66.4628","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.4628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.shef.ac.uk/~fabio/paperi/learningpinocchio.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W121179280","https://openalex.org/W138033052","https://openalex.org/W200042785","https://openalex.org/W1499578805","https://openalex.org/W1522202524","https://openalex.org/W1553019137","https://openalex.org/W1553229631","https://openalex.org/W1601355003","https://openalex.org/W1602152045","https://openalex.org/W1888943520","https://openalex.org/W1971563386","https://openalex.org/W1986469830","https://openalex.org/W1999595522","https://openalex.org/W2057404345","https://openalex.org/W2126185232","https://openalex.org/W2162340487"],"related_works":["https://openalex.org/W1584537303","https://openalex.org/W4226099950","https://openalex.org/W2347401120","https://openalex.org/W2750549761","https://openalex.org/W28826848","https://openalex.org/W2122272819","https://openalex.org/W4367156293","https://openalex.org/W2126185232","https://openalex.org/W4243376815","https://openalex.org/W173181243"],"abstract_inverted_index":{"The":[0,19],"new":[1],"frontier":[2],"of":[3,15,92,114],"research":[4],"on":[5],"Information":[6,47],"Extraction":[7,48],"from":[8,49],"texts":[9,50],"is":[10,22,35,52],"portability":[11],"without":[12],"any":[13],"knowledge":[14],"Natural":[16],"Language":[17],"Processing.":[18],"market":[20],"potential":[21],"very":[23],"large":[24],"in":[25],"principle,":[26],"provided":[27],"that":[28,51],"a":[29,43,90],"suitable":[30],"easy-to-use":[31],"and":[32,56,65,88,122],"effective":[33],"methodology":[34],"provided.":[36],"In":[37,77],"this":[38,78,115],"paper":[39,79],"we":[40,80,98,109],"describe":[41],"LearningPinocchio,":[42],"system":[44],"for":[45,74,118],"adaptive":[46],"having":[53],"good":[54],"commercial":[55],"scientific":[57],"success.":[58],"Real":[59],"world":[60,120],"applications":[61,93,121],"have":[62,68],"been":[63,69],"built":[64],"evaluation":[66,102],"licenses":[67],"released":[70],"to":[71],"external":[72],"companies":[73],"application":[75],"development.":[76],"outline":[81],"the":[82,86,111],"basic":[83],"algorithm":[84],"behind":[85],"scenes":[87],"present":[89],"number":[91],"developed":[94],"with":[95],"LearningPinocchio.":[96],"Then":[97],"report":[99],"about":[100],"an":[101,105],"performed":[103],"by":[104],"independent":[106],"company.":[107],"Finally,":[108],"discuss":[110],"general":[112],"suitability":[113],"IE":[116],"technology":[117],"real":[119],"draw":[123],"some":[124],"conclusion.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
