{"id":"https://openalex.org/W2038007732","doi":"https://doi.org/10.1007/s10579-012-9187-y","title":"Automatic normalization of short texts by combining statistical and rule-based techniques","display_name":"Automatic normalization of short texts by combining statistical and rule-based techniques","publication_year":2012,"publication_date":"2012-05-23","ids":{"openalex":"https://openalex.org/W2038007732","doi":"https://doi.org/10.1007/s10579-012-9187-y","mag":"2038007732"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-012-9187-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10579-012-9187-y","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","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/A5074210163","display_name":"Marta R. Costa\u2010juss\u00e0","orcid":"https://orcid.org/0000-0002-5703-520X"},"institutions":[{"id":"https://openalex.org/I4210147025","display_name":"Barcelona Media","ror":"https://ror.org/047yj9455","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210147025"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Marta R. Costa-juss\u00e0","raw_affiliation_strings":["Barcelona Media Innovation Center, Av. Diagonal 177, 08018, Barcelona, Spain","Barcelona Media Innovation Center, Barcelona, Spain 08018#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Media Innovation Center, Av. Diagonal 177, 08018, Barcelona, Spain","institution_ids":["https://openalex.org/I4210147025"]},{"raw_affiliation_string":"Barcelona Media Innovation Center, Barcelona, Spain 08018#TAB#","institution_ids":["https://openalex.org/I4210147025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022050902","display_name":"Rafael E. Banchs","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rafael E. Banchs","raw_affiliation_strings":["Institute for Infocomm Research, 1 Fusionopolis Way, Singapore, 138632, Singapore","Institute for Infocomm Research, Singapore,Singapore,138632"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, 1 Fusionopolis Way, Singapore, 138632, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research, Singapore,Singapore,138632","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074210163"],"corresponding_institution_ids":["https://openalex.org/I4210147025"],"apc_list":null,"apc_paid":null,"fwci":1.7685,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86574611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"47","issue":"1","first_page":"179","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9987999796867371,"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":0.9907000064849854,"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/normalization","display_name":"Normalization (sociology)","score":0.805903971195221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7927473783493042},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6176295280456543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5886979103088379},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.5697932839393616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5679590702056885},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5658114552497864},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.45276015996932983},{"id":"https://openalex.org/keywords/rule-based-system","display_name":"Rule-based system","score":0.4184494912624359},{"id":"https://openalex.org/keywords/database-normalization","display_name":"Database normalization","score":0.4163411855697632},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38597795367240906},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3485795259475708},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.30606526136398315},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.17770564556121826}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.805903971195221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7927473783493042},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6176295280456543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5886979103088379},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.5697932839393616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5679590702056885},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5658114552497864},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.45276015996932983},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.4184494912624359},{"id":"https://openalex.org/C162984825","wikidata":"https://www.wikidata.org/wiki/Q339072","display_name":"Database normalization","level":3,"score":0.4163411855697632},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38597795367240906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3485795259475708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30606526136398315},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.17770564556121826},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10579-012-9187-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10579-012-9187-y","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/102182","is_oa":false,"landing_page_url":"https://hdl.handle.net/2117/102182","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320334744","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1631260214","https://openalex.org/W1969974515","https://openalex.org/W1979102019","https://openalex.org/W2006969979","https://openalex.org/W2087735403","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2136332941","https://openalex.org/W2146574666","https://openalex.org/W2151616790","https://openalex.org/W2154124206","https://openalex.org/W2163942301","https://openalex.org/W2288542159","https://openalex.org/W2401082558","https://openalex.org/W2895810819","https://openalex.org/W2998215494","https://openalex.org/W4211138600","https://openalex.org/W4254408171","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2376415519","https://openalex.org/W4294769427","https://openalex.org/W1601381279","https://openalex.org/W1895908943","https://openalex.org/W4225667838","https://openalex.org/W4281893144","https://openalex.org/W2374747083","https://openalex.org/W4388254351","https://openalex.org/W4386270999","https://openalex.org/W2385734057"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2016-06-24T00:00:00"}
