{"id":"https://openalex.org/W2604143972","doi":"https://doi.org/10.21437/interspeech.2017-1663","title":"Crowdsourcing Universal Part-of-Speech Tags for Code-Switching","display_name":"Crowdsourcing Universal Part-of-Speech Tags for Code-Switching","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2604143972","doi":"https://doi.org/10.21437/interspeech.2017-1663","mag":"2604143972"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1663","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-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/A5109207771","display_name":"V\u00edctor Soto","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Victor Soto","raw_affiliation_strings":["Columbia University, NY, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045037642","display_name":"Julia Hirschberg","orcid":"https://orcid.org/0000-0003-0689-7616"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Hirschberg","raw_affiliation_strings":["Columbia University, NY, USA"],"affiliations":[{"raw_affiliation_string":"Columbia University, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109207771"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":1.7552,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88166015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T12031","display_name":"Speech and dialogue systems","score":0.9984999895095825,"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":0.9950000047683716,"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":0.8301345109939575},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7645062208175659},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7412121891975403},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6878675222396851},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6404999494552612},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.6318933367729187},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5612448453903198},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5583131313323975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5336936712265015},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4710500240325928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.437777042388916},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14934080839157104},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14721447229385376},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10513761639595032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8301345109939575},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7645062208175659},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7412121891975403},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6878675222396851},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6404999494552612},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.6318933367729187},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5612448453903198},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5583131313323975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5336936712265015},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4710500240325928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.437777042388916},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14934080839157104},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14721447229385376},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10513761639595032},{"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},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-1663","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W23077562","https://openalex.org/W900993354","https://openalex.org/W1632114991","https://openalex.org/W1878590289","https://openalex.org/W1898139072","https://openalex.org/W1911338136","https://openalex.org/W2127849236","https://openalex.org/W2129142580","https://openalex.org/W2129494713","https://openalex.org/W2135360533","https://openalex.org/W2143995218","https://openalex.org/W2145111356","https://openalex.org/W2251818274","https://openalex.org/W2598499942","https://openalex.org/W3098911752"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114"],"abstract_inverted_index":{"Code-switching":[0],"is":[1,22,42,131,148,168,184],"the":[2,25,46,67,76,114,123,140,145,165,178,191],"phenomenon":[3],"by":[4,45],"which":[5,84,94,118],"bilingual":[6],"speakers":[7],"switch":[8],"between":[9,160,169,185],"multiple":[10],"languages":[11],"during":[12],"communication.The":[13],"importance":[14],"of":[15,48,71,87,103,144],"developing":[16],"language":[17],"technologies":[18],"for":[19,36,56,66,113,135,173],"codeswitching":[20],"data":[21,54,116],"immense,":[23],"given":[24],"large":[26],"populations":[27],"that":[28],"routinely":[29],"code-switch.High-quality":[30],"linguistic":[31],"annotations":[32],"are":[33,89,96,120],"extremely":[34],"valuable":[35],"any":[37],"NLP":[38],"task,":[39],"and":[40,107,133,139,164,171,177,187],"performance":[41],"often":[43],"limited":[44],"amount":[47],"high-quality":[49],"labeled":[50,90],"data.However,":[51],"little":[52],"such":[53],"exists":[55],"code-switching.In":[57],"this":[58],"paper,":[59],"we":[60],"describe":[61],"crowd-sourcing":[62],"universal":[63,141],"part-of-speech":[64,182],"tags":[65,183],"Miami":[68],"Bangor":[69],"Corpus":[70],"Spanish-English":[72],"code-switched":[73],"speech.We":[74],"split":[75],"annotation":[77,146],"task":[78],"into":[79],"three":[80,175],"subtasks:":[81],"one":[82,92],"in":[83,93,117],"a":[85,101,108,126,136],"subset":[86,102],"tokens":[88],"automatically,":[91],"questions":[95,119,153],"specifically":[97],"designed":[98],"to":[99,122],"disambiguate":[100],"high":[104],"frequency":[105],"words,":[106],"more":[109],"general":[110],"cascaded":[111],"approach":[112],"remaining":[115],"displayed":[121],"worker":[124],"following":[125],"decision":[127],"tree":[128],"structure.Each":[129],"subtask":[130],"extended":[132],"adapted":[134],"multilingual":[137],"setting":[138],"tagset.The":[142],"quality":[143],"process":[147],"measured":[149],"using":[150],"hidden":[151],"check":[152],"annotated":[154],"with":[155],"gold":[156,161],"labels.The":[157],"overall":[158],"agreement":[159],"standard":[162],"labels":[163,176],"majority":[166],"vote":[167],"0.95":[170],"0.96":[172],"just":[174],"average":[179],"recall":[180],"across":[181],"0.87":[186],"0.99,":[188],"depending":[189],"on":[190],"task.":[192]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}