{"id":"https://openalex.org/W2174008607","doi":"https://doi.org/10.3233/978-1-58603-975-2-175","title":"Finite State Models for the Generation of Large Corpora of Natural Language Texts","display_name":"Finite State Models for the Generation of Large Corpora of Natural Language Texts","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2174008607","doi":"https://doi.org/10.3233/978-1-58603-975-2-175","mag":"2174008607"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-58603-975-2-175","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-58603-975-2-175","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","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/A5045684463","display_name":"Domenico Cantone","orcid":"https://orcid.org/0000-0002-1306-1166"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cantone Domenico","raw_affiliation_strings":["Universit\u00e0 di Catania, Dipartimento di Matematica e Informatica, Viale Andrea Doria 6, I-95125 Catania, Italy, {cantone | cristofaro | faro | giaquinta}@dmi.unict.it#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Catania, Dipartimento di Matematica e Informatica, Viale Andrea Doria 6, I-95125 Catania, Italy, {cantone | cristofaro | faro | giaquinta}@dmi.unict.it#TAB#","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014100286","display_name":"Salvatore Cristofaro","orcid":"https://orcid.org/0000-0001-7188-389X"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cristofaro Salvatore","raw_affiliation_strings":["Universit\u00e0 di Catania, Dipartimento di Matematica e Informatica, Viale Andrea Doria 6, I-95125 Catania, Italy, {cantone | cristofaro | faro | giaquinta}@dmi.unict.it#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Catania, Dipartimento di Matematica e Informatica, Viale Andrea Doria 6, I-95125 Catania, Italy, {cantone | cristofaro | faro | giaquinta}@dmi.unict.it#TAB#","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105877451","display_name":"Simone Faro","orcid":"https://orcid.org/0000-0001-5937-5796"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Faro Simone","raw_affiliation_strings":["Universit\u00e0 di Catania, Dipartimento di Matematica e Informatica, Viale Andrea Doria 6, I-95125 Catania, Italy, {cantone | cristofaro | faro | giaquinta}@dmi.unict.it#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Catania, Dipartimento di Matematica e Informatica, Viale Andrea Doria 6, I-95125 Catania, Italy, {cantone | cristofaro | faro | giaquinta}@dmi.unict.it#TAB#","institution_ids":["https://openalex.org/I39063666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026659686","display_name":"Emanuele Giaquinta","orcid":"https://orcid.org/0000-0002-9473-3971"},"institutions":[{"id":"https://openalex.org/I39063666","display_name":"University of Catania","ror":"https://ror.org/03a64bh57","country_code":"IT","type":"education","lineage":["https://openalex.org/I39063666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giaquinta Emanuele","raw_affiliation_strings":["Universit\u00e0 di Catania, Dipartimento di Matematica e Informatica, Viale Andrea Doria 6, I-95125 Catania, Italy, {cantone | cristofaro | faro | giaquinta}@dmi.unict.it#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Catania, Dipartimento di Matematica e Informatica, Viale Andrea Doria 6, I-95125 Catania, Italy, {cantone | cristofaro | faro | giaquinta}@dmi.unict.it#TAB#","institution_ids":["https://openalex.org/I39063666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.18187919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"175","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5668345093727112},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5598085522651672},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5413792133331299},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5256144404411316},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5123275518417358},{"id":"https://openalex.org/keywords/finite-state","display_name":"Finite state","score":0.45973220467567444},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.45030224323272705},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.437447726726532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4161268472671509},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.2933014929294586},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.16969341039657593},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13420283794403076},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.07546976208686829}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5668345093727112},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5598085522651672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5413792133331299},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5256144404411316},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5123275518417358},{"id":"https://openalex.org/C2983497884","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite state","level":3,"score":0.45973220467567444},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45030224323272705},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.437447726726532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4161268472671509},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2933014929294586},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.16969341039657593},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13420283794403076},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.07546976208686829},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-58603-975-2-175","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-58603-975-2-175","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"mag:2174008607","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/fsmnlp/fsmnlp2008.html#CantoneCFG08","pdf_url":null,"source":{"id":"https://openalex.org/S4306418424","display_name":"Finite-State Methods and Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Finite-State Methods and Natural Language Processing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W124331494","https://openalex.org/W167823983","https://openalex.org/W177913229","https://openalex.org/W1595313252","https://openalex.org/W2031469331","https://openalex.org/W2038180954","https://openalex.org/W2122092249","https://openalex.org/W2769133055"],"related_works":["https://openalex.org/W2955859849","https://openalex.org/W2122804826","https://openalex.org/W2152921782","https://openalex.org/W382594479","https://openalex.org/W2470045054","https://openalex.org/W2575772232","https://openalex.org/W2151245229","https://openalex.org/W2140902089","https://openalex.org/W2988746243","https://openalex.org/W1510553545"],"abstract_inverted_index":{"Natural":[0],"languages":[1],"are":[2],"probably":[3],"one":[4],"of":[5,10,27,29,51,54,66],"the":[6,45,49],"most":[7],"common":[8],"type":[9],"input":[11,28],"for":[12,38],"text":[13],"processing":[14],"algorithms.":[15],"Therefore,":[16],"it":[17],"is":[18],"often":[19],"desirable":[20],"to":[21,48],"have":[22],"a":[23,64],"large":[24],"training/testing":[25],"set":[26,65],"this":[30],"kind,":[31],"especially":[32],"when":[33],"dealing":[34],"with":[35,70],"algorithms":[36],"tuned":[37],"natural":[39,55],"language":[40,56],"texts.":[41],"In":[42],"many":[43],"cases":[44],"problem":[46],"due":[47],"lack":[50],"big":[52],"corpus":[53],"texts":[57],"can":[58],"be":[59],"solved":[60],"by":[61,74],"simply":[62],"concatenating":[63],"collected":[67],"texts,":[68],"even":[69],"heterogeneous":[71],"contexts":[72],"and":[73],"different":[75],"authors.":[76]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}
