{"id":"https://openalex.org/W2912564276","doi":"https://doi.org/10.18653/v1/w18-6101","title":"Inducing a lexicon of sociolinguistic variables from code-mixed text","display_name":"Inducing a lexicon of sociolinguistic variables from code-mixed text","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2912564276","doi":"https://doi.org/10.18653/v1/w18-6101","mag":"2912564276"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-6101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6101","pdf_url":"https://www.aclweb.org/anthology/W18-6101.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 2018 EMNLP Workshop W-NUT: The 4th 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/W18-6101.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042154617","display_name":"Philippa Shoemark","orcid":"https://orcid.org/0000-0003-4750-5447"},"institutions":[{"id":"https://openalex.org/I4210128853","display_name":"China Datang Corporation (China)","ror":"https://ror.org/033mgm122","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Philippa Shoemark","raw_affiliation_strings":["School of Informatics University of Edinburgh","Data Science CDT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics University of Edinburgh","institution_ids":[]},{"raw_affiliation_string":"Data Science CDT","institution_ids":["https://openalex.org/I4210128853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045985704","display_name":"James Kirby","orcid":"https://orcid.org/0000-0002-0502-5245"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Kirby","raw_affiliation_strings":["Dept. of Linguistics and English Language","University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Linguistics and English Language","institution_ids":[]},{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9993000030517578,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T13173","display_name":"Gender Studies in Language","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/3318","display_name":"Gender Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7446987628936768},{"id":"https://openalex.org/keywords/sociolinguistics","display_name":"Sociolinguistics","score":0.6716362833976746},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6634767055511475},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6146571636199951},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5719074010848999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5684455037117004},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.5494177341461182},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5475455522537231},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5168350338935852},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.49949193000793457},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.47605061531066895},{"id":"https://openalex.org/keywords/nothing","display_name":"Nothing","score":0.45231786370277405},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0885118842124939}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7446987628936768},{"id":"https://openalex.org/C28519872","wikidata":"https://www.wikidata.org/wiki/Q160845","display_name":"Sociolinguistics","level":2,"score":0.6716362833976746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6634767055511475},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6146571636199951},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5719074010848999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5684455037117004},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.5494177341461182},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5475455522537231},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5168350338935852},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.49949193000793457},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.47605061531066895},{"id":"https://openalex.org/C136815107","wikidata":"https://www.wikidata.org/wiki/Q154242","display_name":"Nothing","level":2,"score":0.45231786370277405},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0885118842124939},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/w18-6101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6101","pdf_url":"https://www.aclweb.org/anthology/W18-6101.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 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/3d576ee1-2d9d-4b1b-82bf-77164c12e0b4","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/3d576ee1-2d9d-4b1b-82bf-77164c12e0b4","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Shoemark, P, Kirby, J & Goldwater, S 2018, Inducing a lexicon of sociolinguistic variables from code-mixed text. in 2018 The 4th Workshop on Noisy User-generated Text (W-NUT) : Nov 1, 2018, Brussels, Belgium (at EMNLP 2018). Brussels, Belgium , pp. 1-6, 4th Workshop on Noisy User-generated Text (W-NUT), Brussels, Belgium, 1/11/18. < http://aclweb.org/anthology/W18-6101 >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/3d576ee1-2d9d-4b1b-82bf-77164c12e0b4","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/3d576ee1-2d9d-4b1b-82bf-77164c12e0b4","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.18653/v1/w18-6101","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-6101","pdf_url":"https://www.aclweb.org/anthology/W18-6101.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 2018 EMNLP Workshop W-NUT: The 4th Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G4437068315","display_name":"EPSRC Centre for Doctoral Training in Data Science","funder_award_id":"EP/L016427/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320332","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2912564276.pdf","grobid_xml":"https://content.openalex.org/works/W2912564276.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W400491622","https://openalex.org/W1529864641","https://openalex.org/W1824181300","https://openalex.org/W2140406733","https://openalex.org/W2153579005","https://openalex.org/W2157133710","https://openalex.org/W2165279024","https://openalex.org/W2169200297","https://openalex.org/W2207485025","https://openalex.org/W2234751941","https://openalex.org/W2252027930","https://openalex.org/W2290025337","https://openalex.org/W2292415828","https://openalex.org/W2483215953","https://openalex.org/W2591139331","https://openalex.org/W2604475875","https://openalex.org/W2606131891","https://openalex.org/W2793186654","https://openalex.org/W2950018712","https://openalex.org/W3010805239","https://openalex.org/W3098567718","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2216420239","https://openalex.org/W3011492772","https://openalex.org/W2800570524","https://openalex.org/W2499122376","https://openalex.org/W2808813869","https://openalex.org/W2109915140","https://openalex.org/W2315519183","https://openalex.org/W2103493327","https://openalex.org/W2375097772","https://openalex.org/W3152601163"],"abstract_inverted_index":{"Sociolinguistics":[0],"is":[1],"often":[2],"concerned":[3],"with":[4,45],"how":[5],"variants":[6],"of":[7,28,71,84,89,123],"a":[8,53],"linguistic":[9,47],"item":[10],"(e.g.,":[11],"nothing":[12],"vs.":[13],"nothin')":[14],"are":[15],"used":[16,118],"by":[17],"different":[18,22,69],"groups":[19],"or":[20],"in":[21,104],"situations.":[23],"We":[24,51],"introduce":[25],"the":[26,77],"task":[27],"inducing":[29],"lexical":[30],"variables":[31],"from":[32,108],"code-mixed":[33,78],"text:":[34],"that":[35,114],"is,":[36],"identifying":[37,56],"equivalence":[38],"pairs":[39,59,70,125],"such":[40],"as":[41,76,126],"(football,":[42],"fitba)":[43],"along":[44],"their":[46],"code":[48],"(footballBritish,":[49],"fitbaScottish).":[50],"adapt":[52],"framework":[54,107],"for":[55,87],"genderbiased":[57],"word":[58],"to":[60,110,119],"this":[61,106],"new":[62],"task,":[63],"and":[64,93],"present":[65],"results":[66,96],"on":[67],"three":[68,91],"English":[72],"dialects,":[73],"using":[74],"tweets":[75],"text.":[79],"Our":[80,102],"system":[81],"achieves":[82],"precision":[83],"over":[85],"70%":[86],"two":[88],"these":[90],"datasets,":[92],"produces":[94],"useful":[95],"even":[97],"without":[98],"extensive":[99],"parameter":[100],"tuning.":[101],"success":[103],"adapting":[105],"gender":[109],"language":[111],"variety":[112],"suggests":[113],"it":[115],"could":[116],"be":[117],"discover":[120],"other":[121],"types":[122],"analogous":[124],"well.":[127]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}