{"id":"https://openalex.org/W2888979970","doi":"https://doi.org/10.18653/v1/w18-5009","title":"Automatic Token and Turn Level Language Identification for Code-Switched Text Dialog: An Analysis Across Language Pairs and Corpora","display_name":"Automatic Token and Turn Level Language Identification for Code-Switched Text Dialog: An Analysis Across Language Pairs and Corpora","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2888979970","doi":"https://doi.org/10.18653/v1/w18-5009","mag":"2888979970"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w18-5009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5009","pdf_url":"https://www.aclweb.org/anthology/W18-5009.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 19th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W18-5009.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068455745","display_name":"Vikram Ramanarayanan","orcid":"https://orcid.org/0000-0001-7810-2769"},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vikram Ramanarayanan","raw_affiliation_strings":["Educational Testing Service R&D 90 New Montgomery St, #1500 San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service R&D 90 New Montgomery St, #1500 San Francisco, CA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063307617","display_name":"Robert Pugh","orcid":null},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Pugh","raw_affiliation_strings":["Educational Testing Service R&D 90 New Montgomery St, #1500 San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service R&D 90 New Montgomery St, #1500 San Francisco, CA","institution_ids":["https://openalex.org/I1341030882"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068455745"],"corresponding_institution_ids":["https://openalex.org/I1341030882"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.09181626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"80","last_page":"88"},"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9954000115394592,"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":0.8116787672042847},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.6952798366546631},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6471414566040039},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6277636289596558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.590830385684967},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5549879670143127},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5518683195114136},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4904327094554901},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.486855685710907},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4557560980319977},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.44670283794403076},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.440321683883667},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41998130083084106},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39814773201942444},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.34865835309028625},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1083480715751648},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10193848609924316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116787672042847},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.6952798366546631},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6471414566040039},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6277636289596558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.590830385684967},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5549879670143127},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5518683195114136},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4904327094554901},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.486855685710907},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4557560980319977},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.44670283794403076},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.440321683883667},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41998130083084106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39814773201942444},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34865835309028625},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1083480715751648},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10193848609924316},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w18-5009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5009","pdf_url":"https://www.aclweb.org/anthology/W18-5009.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 19th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w18-5009","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w18-5009","pdf_url":"https://www.aclweb.org/anthology/W18-5009.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 19th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888979970.pdf","grobid_xml":"https://content.openalex.org/works/W2888979970.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W99394049","https://openalex.org/W880632652","https://openalex.org/W1549308892","https://openalex.org/W1565921419","https://openalex.org/W1614298861","https://openalex.org/W1972711991","https://openalex.org/W1997489316","https://openalex.org/W2002019621","https://openalex.org/W2013489815","https://openalex.org/W2023570662","https://openalex.org/W2023946512","https://openalex.org/W2064675550","https://openalex.org/W2098002964","https://openalex.org/W2123660869","https://openalex.org/W2134036914","https://openalex.org/W2147880316","https://openalex.org/W2176685020","https://openalex.org/W2250539671","https://openalex.org/W2250548009","https://openalex.org/W2251149908","https://openalex.org/W2251238585","https://openalex.org/W2251678408","https://openalex.org/W2296283641","https://openalex.org/W2557418006","https://openalex.org/W2560987006","https://openalex.org/W2561841276","https://openalex.org/W2566026285","https://openalex.org/W2738180183","https://openalex.org/W2746009407","https://openalex.org/W2949952998","https://openalex.org/W2950577311","https://openalex.org/W2976985074","https://openalex.org/W4236564204","https://openalex.org/W4237155282"],"related_works":["https://openalex.org/W4236658683","https://openalex.org/W2980207396","https://openalex.org/W2020463334","https://openalex.org/W3156493709","https://openalex.org/W2026182709","https://openalex.org/W226586525","https://openalex.org/W1998541766","https://openalex.org/W2064542902","https://openalex.org/W2262900283","https://openalex.org/W1985349217"],"abstract_inverted_index":{"We":[0,54,79],"examine":[1,35,81],"the":[2,27,36,82,102],"efficacy":[3,83],"of":[4,14,38,51,58,84],"various":[5],"feature-learner":[6],"combinations":[7],"for":[8],"language":[9,42,107],"identification":[10],"in":[11,90],"different":[12,49],"types":[13],"text-based":[15],"code-switched":[16,52],"interactionshuman-human":[17],"dialog,":[18,20],"human-machine":[19],"as":[21,23],"well":[22],"monolog":[24],"-at":[25],"both":[26],"token":[28],"and":[29,44,63,75,87,93,109],"turn":[30],"levels.":[31],"In":[32],"order":[33],"to":[34],"generalization":[37],"such":[39],"methods":[40],"across":[41,106],"pairs":[43,108],"datasets,":[45],"we":[46],"analyze":[47],"ten":[48],"datasets":[50],"text.":[53],"extract":[55],"a":[56],"variety":[57],"character-and":[59],"word-based":[60],"text":[61,98],"features":[62,89],"pass":[64],"them":[65],"into":[66],"multiple":[67],"learners,":[68],"including":[69],"conditional":[70],"random":[71],"fields,":[72],"logistic":[73],"regressors,":[74],"recurrent":[76],"neural":[77],"networks.":[78],"further":[80],"character-level":[85],"embedding":[86],"GloVe":[88],"improving":[91],"performance":[92],"observe":[94],"that":[95],"our":[96],"best-performing":[97],"system":[99],"significantly":[100],"outperforms":[101],"majority":[103],"vote":[104],"baseline":[105],"datasets.":[110]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}