{"id":"https://openalex.org/W2250801584","doi":"https://doi.org/10.18653/v1/d15-1150","title":"Part-of-speech Taggers for Low-resource Languages using CCA Features","display_name":"Part-of-speech Taggers for Low-resource Languages using CCA Features","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250801584","doi":"https://doi.org/10.18653/v1/d15-1150","mag":"2250801584"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d15-1150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1150","pdf_url":"https://www.aclweb.org/anthology/D15-1150.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 2015 Conference on Empirical Methods in Natural Language Processing","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/D15-1150.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010305620","display_name":"Young\u2010Bum Kim","orcid":"https://orcid.org/0000-0001-9471-6330"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Young-Bum Kim","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039445725","display_name":"Benjamin Snyder","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Snyder","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, WI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, WI","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072875068","display_name":"Ruhi Sarikaya","orcid":"https://orcid.org/0000-0003-2676-2831"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruhi Sarikaya","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T13629","display_name":"Text Readability and Simplification","score":0.9854999780654907,"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":0.842257022857666},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6224456429481506},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6209648847579956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.598822295665741},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5738948583602905},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5590032339096069},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5547764897346497},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5508353114128113},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.5060068964958191},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3608208894729614},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08715403079986572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.842257022857666},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6224456429481506},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6209648847579956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.598822295665741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5738948583602905},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5590032339096069},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5547764897346497},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5508353114128113},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.5060068964958191},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3608208894729614},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08715403079986572},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/d15-1150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1150","pdf_url":"https://www.aclweb.org/anthology/D15-1150.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.5994","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.5994","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/D/D15/D15-1150.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d15-1150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1150","pdf_url":"https://www.aclweb.org/anthology/D15-1150.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250801584.pdf","grobid_xml":"https://content.openalex.org/works/W2250801584.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1419521840","https://openalex.org/W1506525786","https://openalex.org/W1536675765","https://openalex.org/W1574126082","https://openalex.org/W1602492977","https://openalex.org/W1605111415","https://openalex.org/W2016630033","https://openalex.org/W2025341678","https://openalex.org/W2048500237","https://openalex.org/W2100236795","https://openalex.org/W2118585731","https://openalex.org/W2121954058","https://openalex.org/W2125290066","https://openalex.org/W2130451992","https://openalex.org/W2131134557","https://openalex.org/W2142523187","https://openalex.org/W2143995218","https://openalex.org/W2145110208","https://openalex.org/W2152691628","https://openalex.org/W2154368244","https://openalex.org/W2161044106","https://openalex.org/W2165256480","https://openalex.org/W2169724380","https://openalex.org/W2171183582","https://openalex.org/W2174400750","https://openalex.org/W2250486491","https://openalex.org/W2250508463","https://openalex.org/W2251184803","https://openalex.org/W2251249950","https://openalex.org/W2251816562","https://openalex.org/W2252070015","https://openalex.org/W2252207888","https://openalex.org/W2295800284","https://openalex.org/W2396314717","https://openalex.org/W2800695765","https://openalex.org/W3010865323","https://openalex.org/W3215084437","https://openalex.org/W4237723258","https://openalex.org/W4302455086"],"related_works":["https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W1980100242","https://openalex.org/W2530420969","https://openalex.org/W2051187167","https://openalex.org/W4315815996"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,45],"address":[4],"the":[5,27,94],"challenge":[6],"of":[7,34,67,102],"creating":[8],"accurate":[9],"and":[10,30,84],"robust":[11],"partof-speech":[12],"taggers":[13],"for":[14,105],"low-resource":[15],"languages.":[16,69],"We":[17,70],"propose":[18],"a":[19,31,64,72,90,112],"method":[20,98],"that":[21,53],"leverages":[22],"existing":[23],"parallel":[24],"data":[25],"between":[26],"target":[28],"language":[29],"large":[32],"set":[33],"resourcerich":[35],"languages":[36,106],"without":[37],"ancillary":[38],"resources":[39],"such":[40],"as":[41,58,60],"tag":[42,82],"dictionaries.":[43],"Crucially,":[44],"use":[46,85],"CCA":[47,95],"to":[48,76,88],"induce":[49],"latent":[50],"word":[51],"representations":[52],"incorporate":[54],"cross-genre":[55],"distributional":[56],"cues,":[57],"well":[59],"projected":[61],"tags":[62],"from":[63],"full":[65],"array":[66],"resource-rich":[68],"develop":[71],"probability-based":[73],"confidence":[74],"model":[75],"identify":[77],"words":[78,87],"with":[79,107],"highly":[80],"likely":[81],"projections":[83],"these":[86],"train":[89],"multi-class":[91],"SVM":[92],"using":[93],"features.":[96],"Our":[97],"yields":[99],"average":[100],"performance":[101],"85%":[103],"accuracy":[104],"almost":[108],"no":[109],"resources,":[110],"outperforming":[111],"state-of-the-art":[113],"partiallyobserved":[114],"CRF":[115],"model.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}