{"id":"https://openalex.org/W2108455276","doi":"https://doi.org/10.1017/s1351324997001563","title":"Regular expressions for language engineering","display_name":"Regular expressions for language engineering","publication_year":1996,"publication_date":"1996-12-01","ids":{"openalex":"https://openalex.org/W2108455276","doi":"https://doi.org/10.1017/s1351324997001563","mag":"2108455276"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324997001563","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324997001563","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/A5048002562","display_name":"Lauri Karttunen","orcid":"https://orcid.org/0000-0002-5800-8326"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"L. KARTTUNEN","raw_affiliation_strings":["Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail:","Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail: Lauri.Karttunen@grenoble.rxrc.xerox.com,#TAB#"],"affiliations":[{"raw_affiliation_string":"Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail:","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail: Lauri.Karttunen@grenoble.rxrc.xerox.com,#TAB#","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111896313","display_name":"J-P. CHANOD","orcid":null},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J-P. CHANOD","raw_affiliation_strings":["Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail:","Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail: Jean-Pierre.Chanod@grenoble.rxrc.xerox.com#TAB#"],"affiliations":[{"raw_affiliation_string":"Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail:","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail: Jean-Pierre.Chanod@grenoble.rxrc.xerox.com#TAB#","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039513155","display_name":"Gregory Grefenstette","orcid":"https://orcid.org/0000-0001-8479-049X"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G. GREFENSTETTE","raw_affiliation_strings":["Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail:","Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail: Gregory.Grefenstette@grenoble.rxrc.xerox.com,#TAB#"],"affiliations":[{"raw_affiliation_string":"Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail:","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail: Gregory.Grefenstette@grenoble.rxrc.xerox.com,#TAB#","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029669333","display_name":"A. SCHILLE","orcid":null},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"A. SCHILLE","raw_affiliation_strings":["Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail:","Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail: Anne.Schiller@grenoble.rxrc.xerox.com#TAB#"],"affiliations":[{"raw_affiliation_string":"Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail:","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Rank Xerox Research Centre (RXRC), 6 Chemin de Maupertuis, 38240 Meylan, France. e-mail: Anne.Schiller@grenoble.rxrc.xerox.com#TAB#","institution_ids":["https://openalex.org/I33976269"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048002562"],"corresponding_institution_ids":["https://openalex.org/I33976269"],"apc_list":null,"apc_paid":null,"fwci":10.8156,"has_fulltext":false,"cited_by_count":199,"citation_normalized_percentile":{"value":0.98488251,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"2","issue":"4","first_page":"305","last_page":"328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T11567","display_name":"semigroups and automata theory","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10126","display_name":"Logic, programming, and type systems","score":0.9894000291824341,"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":0.9100169539451599},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.767520546913147},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7307059168815613},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.6769081950187683},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6138861775398254},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5560450553894043},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5555737018585205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32547616958618164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9100169539451599},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.767520546913147},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7307059168815613},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.6769081950187683},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6138861775398254},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5560450553894043},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5555737018585205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32547616958618164}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1017/s1351324997001563","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324997001563","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:10.1.1.111.6490","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.111.6490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.parc.com/istl/members/karttune/publications/jnle-97/rele.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.142.128","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-2.cs.cmu.edu/afs/cs.cmu.edu/project/cmt-55/lti/Courses/711/Class-notes/Kemal-CompMorph/lauri-et-al.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.4880","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.4880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.xrce.xerox.com/publis/mltt/mltt-96-15.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W201288405","https://openalex.org/W1496125727","https://openalex.org/W1513168562","https://openalex.org/W1527398610","https://openalex.org/W1602846073","https://openalex.org/W1775117284","https://openalex.org/W1969134258","https://openalex.org/W1993258438","https://openalex.org/W1993559696","https://openalex.org/W2007624857","https://openalex.org/W2017364694","https://openalex.org/W2053861089","https://openalex.org/W2065700902","https://openalex.org/W2081687495","https://openalex.org/W2097125878","https://openalex.org/W2133065881","https://openalex.org/W2143173740","https://openalex.org/W2170706044","https://openalex.org/W2296035094","https://openalex.org/W2951009239","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1991876452","https://openalex.org/W3136824659","https://openalex.org/W3185922486","https://openalex.org/W2362066624","https://openalex.org/W2293063786","https://openalex.org/W2051250732","https://openalex.org/W4246321749","https://openalex.org/W2911292476","https://openalex.org/W2108455276","https://openalex.org/W4245282765"],"abstract_inverted_index":{"Many":[0],"of":[1,69],"the":[2,36,62],"processing":[3],"steps":[4],"in":[5,49,61,65],"natural":[6,50],"language":[7,51],"engineering":[8],"can":[9],"be":[10],"performed":[11],"using":[12],"finite":[13],"state":[14],"transducers.":[15],"An":[16],"optimal":[17],"way":[18],"to":[19,24,35,56],"create":[20],"such":[21],"transducers":[22],"is":[23,32],"compile":[25],"them":[26],"from":[27,54],"regular":[28,37],"expressions.":[29],"This":[30],"paper":[31,63],"an":[33],"introduction":[34],"expression":[38],"calculus,":[39],"extended":[40],"with":[41],"certain":[42],"operators":[43],"that":[44],"have":[45],"proved":[46],"very":[47],"useful":[48],"applications":[52],"ranging":[53],"tokenization":[55],"light":[57],"parsing.":[58],"The":[59],"examples":[60],"illustrate":[64],"concrete":[66],"detail":[67],"some":[68],"these":[70],"applications.":[71]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}