{"id":"https://openalex.org/W2758128421","doi":"https://doi.org/10.18653/v1/w17-4414","title":"A Text Normalisation System for Non-Standard English Words","display_name":"A Text Normalisation System for Non-Standard English Words","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2758128421","doi":"https://doi.org/10.18653/v1/w17-4414","mag":"2758128421"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-4414","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4414","pdf_url":"https://www.aclweb.org/anthology/W17-4414.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-4414.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069405642","display_name":"Emma Flint","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Emma Flint","raw_affiliation_strings":["Department of Theoretical and Applied Linguistics"],"affiliations":[{"raw_affiliation_string":"Department of Theoretical and Applied Linguistics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086313388","display_name":"Elliot Ford","orcid":"https://orcid.org/0000-0003-4824-9182"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elliot Ford","raw_affiliation_strings":["Department of Theoretical and Applied Linguistics"],"affiliations":[{"raw_affiliation_string":"Department of Theoretical and Applied Linguistics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100996309","display_name":"Olivia Thomas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivia Thomas","raw_affiliation_strings":["Department of Theoretical and Applied Linguistics"],"affiliations":[{"raw_affiliation_string":"Department of Theoretical and Applied Linguistics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069029343","display_name":"Andrew Caines","orcid":"https://orcid.org/0000-0001-9647-4902"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Caines","raw_affiliation_strings":["Department of Theoretical and Applied Linguistics"],"affiliations":[{"raw_affiliation_string":"Department of Theoretical and Applied Linguistics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013999263","display_name":"Paula Buttery","orcid":"https://orcid.org/0000-0003-3874-0656"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Paula Buttery","raw_affiliation_strings":["Computer Laboratory University of Cambridge, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Computer Laboratory University of Cambridge, Cambridge, U.K","institution_ids":["https://openalex.org/I4210096386","https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069405642"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9502,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.89647654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"107","last_page":"115"},"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":0.9944999814033508,"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":0.9930999875068665,"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":0.8075321316719055},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7750748991966248},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6620850563049316},{"id":"https://openalex.org/keywords/spell","display_name":"Spell","score":0.6468295454978943},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5942636132240295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5517758727073669},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4697948694229126},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.45655766129493713},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4411933124065399},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4182703495025635},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3137933909893036},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09993252158164978},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07026946544647217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075321316719055},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7750748991966248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6620850563049316},{"id":"https://openalex.org/C2780957641","wikidata":"https://www.wikidata.org/wiki/Q1999796","display_name":"Spell","level":2,"score":0.6468295454978943},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5942636132240295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5517758727073669},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4697948694229126},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.45655766129493713},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4411933124065399},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4182703495025635},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3137933909893036},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09993252158164978},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07026946544647217},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-4414","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4414","pdf_url":"https://www.aclweb.org/anthology/W17-4414.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-4414","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4414","pdf_url":"https://www.aclweb.org/anthology/W17-4414.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2758128421.pdf","grobid_xml":"https://content.openalex.org/works/W2758128421.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W157541337","https://openalex.org/W158623153","https://openalex.org/W170738816","https://openalex.org/W1521626219","https://openalex.org/W2029571365","https://openalex.org/W2038721957","https://openalex.org/W2101761627","https://openalex.org/W2146867136","https://openalex.org/W2163942301","https://openalex.org/W2164107060","https://openalex.org/W2251237590","https://openalex.org/W2252192936","https://openalex.org/W2339294230","https://openalex.org/W2963196639","https://openalex.org/W4297803344","https://openalex.org/W4300659315"],"related_works":["https://openalex.org/W4287256643","https://openalex.org/W2745258745","https://openalex.org/W4296626305","https://openalex.org/W4254978807","https://openalex.org/W4287269020","https://openalex.org/W4307454463","https://openalex.org/W4287201819","https://openalex.org/W4252852831","https://openalex.org/W2053351408","https://openalex.org/W4253079800"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,9,38,52,59,102],"problem":[4],"of":[5,11,55,84,92,132],"text":[6],"normalisation;":[7],"specifically,":[8],"normalisation":[10,80],"non-standard":[12],"words":[13,18],"(NSWs)":[14],"in":[15,66,101],"English.":[16],"Non-standard":[17],"can":[19,72],"be":[20,35,73],"defined":[21],"as":[22],"those":[23],"word":[24],"tokens":[25],"which":[26,130],"do":[27],"not":[28],"have":[29],"a":[30,49,68,114],"dictionary":[31],"entry,":[32],"and":[33,58,90,112,127],"cannot":[34],"pronounced":[36,74],"using":[37],"usual":[39],"letterto-phoneme":[40],"conversion":[41],"rules;":[42],"e.g.":[43],"lbs,":[44],"99.3%,":[45],"#EMNLP2017.":[46],"NSWs":[47],"pose":[48],"challenge":[50],"to":[51,62,98,122,141],"proper":[53],"functioning":[54],"textto-speech":[56],"technology,":[57],"solution":[60],"is":[61,95],"spell":[63],"them":[64],"out":[65],"such":[67],"way":[69],"that":[70],"they":[71,139],"appropriately.":[75],"We":[76],"describe":[77],"our":[78],"four-stage":[79],"system":[81,117],"made":[82],"up":[83],"components":[85],"for":[86],"detection,":[87],"classification,":[88],"division":[89],"expansion":[91],"NSWs.":[93],"Performance":[94],"favourabe":[96],"compared":[97],"previous":[99],"work":[100],"field":[103],"Further,":[104],"we":[105],"update":[106],"Sproat":[107],"et":[108],"al.'s":[109],"NSW":[110],"taxonomy,":[111],"create":[113],"more":[115],"customisable":[116],"where":[118],"users":[119],"are":[120],"able":[121],"input":[123],"their":[124],"own":[125],"abbreviations":[126],"specify":[128],"into":[129],"variety":[131],"English":[133],"(currently":[134],"available:":[135],"British":[136],"or":[137],"American)":[138],"wish":[140],"normalise.":[142]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}