{"id":"https://openalex.org/W1803932089","doi":"https://doi.org/10.1007/3-540-36456-0_40","title":"A Corpus Balancing Method for Language Model Construction","display_name":"A Corpus Balancing Method for Language Model Construction","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1803932089","doi":"https://doi.org/10.1007/3-540-36456-0_40","mag":"1803932089"},"language":"en","primary_location":{"id":"doi:10.1007/3-540-36456-0_40","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-36456-0_40","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00326515","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053929522","display_name":"Luis Villase\u00f1or-Pineda","orcid":"https://orcid.org/0000-0003-1294-9128"},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Luis Villase\u00f1or-Pineda","raw_affiliation_strings":["Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica (INAOE), Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica (INAOE), Mexico","institution_ids":["https://openalex.org/I39824353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050780136","display_name":"Manuel Montes-y-G\u00f3mez","orcid":"https://orcid.org/0000-0002-7601-501X"},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Manuel Montes-y-G\u00f3mez","raw_affiliation_strings":["Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica (INAOE), Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica (INAOE), Mexico","institution_ids":["https://openalex.org/I39824353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091093312","display_name":"Manuel P\u00e9rez-Couti\u00f1o","orcid":null},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Manuel Alberto P\u00e9rez-Couti\u00f1o","raw_affiliation_strings":["Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica (INAOE), Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica (INAOE), Mexico","institution_ids":["https://openalex.org/I39824353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077485006","display_name":"Dominique Vaufreydaz","orcid":"https://orcid.org/0000-0002-8825-0973"},"institutions":[{"id":"https://openalex.org/I177483745","display_name":"Universit\u00e9 Joseph Fourier","ror":"https://ror.org/02aj0kh94","country_code":"FR","type":"education","lineage":["https://openalex.org/I177483745"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dominique Vaufreydaz","raw_affiliation_strings":["Laboratoire CLIPS-IMAG, Universit\u00e9 Joseph Fourier, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire CLIPS-IMAG, Universit\u00e9 Joseph Fourier, France","institution_ids":["https://openalex.org/I177483745"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.8295,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.73546366,"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":"393","last_page":"401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9224271774291992},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7309356927871704},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6683090925216675},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.6372695565223694},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6078698039054871},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5946562886238098},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.574761688709259},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5114132761955261},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.44192349910736084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3779129981994629},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10226055979728699}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9224271774291992},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7309356927871704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6683090925216675},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.6372695565223694},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6078698039054871},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5946562886238098},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.574761688709259},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5114132761955261},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.44192349910736084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3779129981994629},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10226055979728699},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/3-540-36456-0_40","is_oa":false,"landing_page_url":"https://doi.org/10.1007/3-540-36456-0_40","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.230.9053","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.230.9053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/32/65/15/PDF/Villasenor03a.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.5222","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.5222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ccc.inaoep.mx/~mmontesg/publicaciones/2003/CorpusBalancing-CicLing03.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.612.4592","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.612.4592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-prima.inrialpes.fr/Vaufreydaz/Telechargement/Villasenor03a.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00326515v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00326515","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Fourth International Conference on Intelligent Text Processing and Computational Linguistics (CICLing-2003), Feb 2003, Mexico City, Mexico. 9 p","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00326515v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00326515","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Fourth International Conference on Intelligent Text Processing and Computational Linguistics (CICLing-2003), Feb 2003, Mexico City, Mexico. 9 p","raw_type":"Conference papers"},"sustainable_development_goals":[{"display_name":"No poverty","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W21092007","https://openalex.org/W92576643","https://openalex.org/W136902465","https://openalex.org/W182831726","https://openalex.org/W1502904630","https://openalex.org/W1579838312","https://openalex.org/W1605162775","https://openalex.org/W1651266083","https://openalex.org/W1860584505","https://openalex.org/W2154127093","https://openalex.org/W6607467106"],"related_works":["https://openalex.org/W2375537499","https://openalex.org/W2516977220","https://openalex.org/W3096124370","https://openalex.org/W2794113965","https://openalex.org/W1982878818","https://openalex.org/W2384280299","https://openalex.org/W2366526038","https://openalex.org/W2183648197","https://openalex.org/W99386505","https://openalex.org/W3087106119"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
