{"id":"https://openalex.org/W2251131759","doi":"https://doi.org/10.3115/v1/p14-2110","title":"Learning Polylingual Topic Models from Code-Switched Social Media Documents","display_name":"Learning Polylingual Topic Models from Code-Switched Social Media Documents","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251131759","doi":"https://doi.org/10.3115/v1/p14-2110","mag":"2251131759"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-2110","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2110","pdf_url":null,"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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/p14-2110","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030248499","display_name":"Nanyun Peng","orcid":"https://orcid.org/0000-0002-8509-6595"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nanyun Peng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377935","display_name":"Yiming Wang","orcid":"https://orcid.org/0000-0002-5932-4371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024437840","display_name":"Mark Dredze","orcid":"https://orcid.org/0000-0002-0422-2474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Dredze","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030248499"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9199,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96307565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"674","last_page":"679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9977999925613403,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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":0.7507897615432739},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5680077075958252},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5237569808959961},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.4146891236305237},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3594161868095398},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32618066668510437},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11637085676193237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507897615432739},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5680077075958252},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5237569808959961},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.4146891236305237},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3594161868095398},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32618066668510437},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11637085676193237},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/p14-2110","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2110","pdf_url":null,"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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.637.8057","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.637.8057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.jhu.edu/~mdredze/publications/2014_acl_cslda.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.654.6274","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.654.6274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/P/P14/P14-2110.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/p14-2110","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2110","pdf_url":null,"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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W201361503","https://openalex.org/W761725120","https://openalex.org/W1445897916","https://openalex.org/W1556255569","https://openalex.org/W1880262756","https://openalex.org/W2002019621","https://openalex.org/W2013489815","https://openalex.org/W2033593667","https://openalex.org/W2063904635","https://openalex.org/W2101761627","https://openalex.org/W2103587173","https://openalex.org/W2106501046","https://openalex.org/W2123660869","https://openalex.org/W2127876534","https://openalex.org/W2135888600","https://openalex.org/W2137268161","https://openalex.org/W2137958601","https://openalex.org/W2140124448","https://openalex.org/W2142889507","https://openalex.org/W2145867197","https://openalex.org/W2146574881","https://openalex.org/W2159426623","https://openalex.org/W2168332560","https://openalex.org/W2182894058","https://openalex.org/W2251238585","https://openalex.org/W2461917396"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2166247150","https://openalex.org/W4243252198","https://openalex.org/W2135396778","https://openalex.org/W1527862632","https://openalex.org/W2118300983","https://openalex.org/W2112962394","https://openalex.org/W3137189469","https://openalex.org/W2740990710","https://openalex.org/W2384847609"],"abstract_inverted_index":{"Code-switched":[0],"documents":[1,33],"are":[2],"common":[3],"in":[4],"social":[5],"media,":[6],"providing":[7],"evidence":[8],"for":[9],"polylingual":[10],"topic":[11,28],"models":[12],"to":[13,34],"infer":[14],"aligned":[15,64],"topics":[16,65],"across":[17],"languages.":[18],"We":[19,39],"present":[20],"Code-Switched":[21],"LDA":[22],"(csLDA),":[23],"which":[24],"in-fers":[25],"language":[26],"specific":[27],"distributions":[29],"based":[30],"on":[31,41],"code-switched":[32],"fa-cilitate":[35],"multi-lingual":[36],"corpus":[37],"analysis.":[38],"experiment":[40],"two":[42],"code-switching":[43],"cor-pora":[44],"(English-Spanish":[45],"Twitter":[46],"data":[47],"and":[48,52,60],"English-Chinese":[49],"Weibo":[50],"data)":[51],"show":[53],"that":[54],"csLDA":[55],"improves":[56],"perplexity":[57],"over":[58],"LDA,":[59],"learns":[61],"semantically":[62],"coherent":[63],"as":[66],"judged":[67],"by":[68],"human":[69],"anno-tators.":[70],"1":[71]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}