{"id":"https://openalex.org/W2250475966","doi":"https://doi.org/10.18653/v1/w15-4318","title":"USZEGED: Correction Type-sensitive Normalization of English Tweets Using Efficiently Indexed n-gram Statistics","display_name":"USZEGED: Correction Type-sensitive Normalization of English Tweets Using Efficiently Indexed n-gram Statistics","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250475966","doi":"https://doi.org/10.18653/v1/w15-4318","mag":"2250475966"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-4318","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4318","pdf_url":"https://www.aclweb.org/anthology/W15-4318.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-4318.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020987552","display_name":"G\u00e1bor Berend","orcid":"https://orcid.org/0000-0002-3845-4978"},"institutions":[{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"G\u00e1bor Berend","raw_affiliation_strings":["University of Szeged Department of Informatics rpd tr 2., 6720 Szeged, Hungary","University of Szeged Department of Informatics \u00c1rp\u00e1d t\u00e9r 2., 6720 Szeged, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Szeged Department of Informatics rpd tr 2., 6720 Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]},{"raw_affiliation_string":"University of Szeged Department of Informatics \u00c1rp\u00e1d t\u00e9r 2., 6720 Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087738988","display_name":"Ervin Tasn\u00e1di","orcid":"https://orcid.org/0000-0002-4713-5397"},"institutions":[{"id":"https://openalex.org/I227486990","display_name":"University of Szeged","ror":"https://ror.org/01pnej532","country_code":"HU","type":"education","lineage":["https://openalex.org/I227486990"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Ervin Tasn\u00e1di","raw_affiliation_strings":["University of Szeged Department of Informatics \u00c1rp\u00e1d t\u00e9r 2., 6720 Szeged, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Szeged Department of Informatics \u00c1rp\u00e1d t\u00e9r 2., 6720 Szeged, Hungary","institution_ids":["https://openalex.org/I227486990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I227486990"],"apc_list":null,"apc_paid":null,"fwci":1.2329,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81894527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.8037201762199402},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.706169843673706},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.702646017074585},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6023300290107727},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5807656645774841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5655459761619568},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5500645637512207},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49321287870407104},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4135863184928894},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3012060523033142},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15658417344093323}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037201762199402},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.706169843673706},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.702646017074585},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6023300290107727},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5807656645774841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5655459761619568},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5500645637512207},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49321287870407104},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4135863184928894},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3012060523033142},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15658417344093323},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w15-4318","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4318","pdf_url":"https://www.aclweb.org/anthology/W15-4318.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},{"id":"pmh:oai:publicatio.bibl.u-szeged.hu:7728","is_oa":true,"landing_page_url":"http://publicatio.bibl.u-szeged.hu/7728/1/W15_4318_u.pdf","pdf_url":"http://publicatio.bibl.u-szeged.hu/7728/1/W15_4318_u.pdf","source":{"id":"https://openalex.org/S4306400675","display_name":"SZTE Publicatio Repozit\u00f3rium (University of Szeged)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I227486990","host_organization_name":"University of Szeged","host_organization_lineage":["https://openalex.org/I227486990"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"K\u00f6nyv r\u00e9sze"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-4318","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-4318","pdf_url":"https://www.aclweb.org/anthology/W15-4318.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250475966.pdf","grobid_xml":"https://content.openalex.org/works/W2250475966.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W157541337","https://openalex.org/W2016443085","https://openalex.org/W2064486843","https://openalex.org/W2096438711","https://openalex.org/W2123661878","https://openalex.org/W2124499489","https://openalex.org/W2124650320","https://openalex.org/W2138738738","https://openalex.org/W2146867136","https://openalex.org/W2147880316","https://openalex.org/W2153848201","https://openalex.org/W2157765050","https://openalex.org/W2169615869","https://openalex.org/W2172112754","https://openalex.org/W2250174865","https://openalex.org/W2250729567","https://openalex.org/W2270414365","https://openalex.org/W3179072117","https://openalex.org/W4233787372"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2787311093","https://openalex.org/W2532616038","https://openalex.org/W4307474317","https://openalex.org/W2147879411","https://openalex.org/W2624072012","https://openalex.org/W2057384730","https://openalex.org/W2008468404","https://openalex.org/W2132221452","https://openalex.org/W2081295016"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,10,29,33,39,63,67,70,87,92,96,107,112,115],"framework":[4,26],"applied":[5],"by":[6],"team":[7],"USZEGED":[8],"at":[9],"\"Lexical":[11],"Normalisation":[12],"for":[13],"English":[14,56,89],"Tweets\"":[15],"shared":[16],"task.":[17],"Our":[18,58,99],"approach":[19,100],"first":[20],"employs":[21],"a":[22,47],"CRFbased":[23],"sequence":[24],"labeling":[25],"to":[27,76],"decide":[28],"kind":[30],"of":[31,50,69,91,104],"corrections":[32],"individual":[34],"tokens":[35],"require,":[36],"then":[37],"performs":[38],"necessary":[40],"modifications":[41],"relying":[42],"on":[43,62],"external":[44],"lexicons":[45],"and":[46],"massive":[48],"collection":[49],"efficiently":[51],"indexed":[52],"n-gram":[53],"statistics":[54],"from":[55,66],"tweets.":[57],"solution":[59],"is":[60,74],"based":[61],"assumption":[64],"that":[65],"context":[68],"OOV":[71,93],"words,":[72],"it":[73],"possible":[75],"reconstruct":[77],"its":[78],"IV":[79],"equivalent,":[80],"as":[81],"there":[82],"are":[83],"users":[84],"who":[85],"use":[86],"standard":[88],"form":[90],"word":[94],"within":[95],"same":[97],"context.":[98],"achieved":[101],"an":[102],"F-score":[103],"0.8052,":[105],"being":[106],"second":[108],"best":[109],"one":[110],"among":[111],"unconstrained":[113],"submissions,":[114],"category":[116],"our":[117],"submission":[118],"also":[119],"belongs":[120],"to.":[121]},"counts_by_year":[{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2016-06-24T00:00:00"}