{"id":"https://openalex.org/W1508791843","doi":"https://doi.org/10.1162/coli_a_00286","title":"Statistical Models for Unsupervised, Semi-Supervised, and Supervised Transliteration Mining","display_name":"Statistical Models for Unsupervised, Semi-Supervised, and Supervised Transliteration Mining","publication_year":2017,"publication_date":"2017-03-28","ids":{"openalex":"https://openalex.org/W1508791843","doi":"https://doi.org/10.1162/coli_a_00286","mag":"1508791843"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00286","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00286","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00286","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00286","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042954793","display_name":"Hassan Sajjad","orcid":"https://orcid.org/0000-0002-8584-6595"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hassan Sajjad","raw_affiliation_strings":["Qatar Computing Research Institute"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027452875","display_name":"Helmut Schmid","orcid":"https://orcid.org/0000-0001-8003-7708"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Helmut Schmid","raw_affiliation_strings":["Ludwig Maximilian University of Munich","Ludwig-Maximilian University of Munich"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Ludwig-Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101957153","display_name":"Alexander Fraser","orcid":"https://orcid.org/0000-0003-4891-682X"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Fraser","raw_affiliation_strings":["Ludwig Maximilian University of Munich","Ludwig-Maximilian University of Munich"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Ludwig-Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071144367","display_name":"Hinrich Sch\u00fctze","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hinrich Sch\u00fctze","raw_affiliation_strings":["Ludwig Maximilian University of Munich","Ludwig-Maximilian University of Munich"],"affiliations":[{"raw_affiliation_string":"Ludwig Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Ludwig-Maximilian University of Munich","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042954793"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2865,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90627342,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"43","issue":"2","first_page":"349","last_page":"375"},"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":0.9972000122070312,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/transliteration","display_name":"Transliteration","score":0.96854567527771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.832166314125061},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7375779747962952},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5974195599555969},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49729350209236145},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4648294448852539},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4451867938041687},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4194164276123047},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3422262668609619},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.335917592048645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24814239144325256},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06895920634269714}],"concepts":[{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.96854567527771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832166314125061},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7375779747962952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5974195599555969},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49729350209236145},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4648294448852539},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4451867938041687},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4194164276123047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3422262668609619},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.335917592048645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24814239144325256},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06895920634269714},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1162/coli_a_00286","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00286","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00286","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f58d9adcf8c44a66bc24d300a76b56d3","is_oa":true,"landing_page_url":"https://doaj.org/article/f58d9adcf8c44a66bc24d300a76b56d3","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 43, Iss 2 (2017)","raw_type":"article"},{"id":"pmh:oai:elib.uni-stuttgart.de:11682/3108","is_oa":true,"landing_page_url":"http://elib.uni-stuttgart.de/handle/11682/3108","pdf_url":null,"source":{"id":"https://openalex.org/S4306401556","display_name":"OPUS Publication Server of the University of Stuttgart (University of Stuttgart)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I100066346","host_organization_name":"University of Stuttgart","host_organization_lineage":["https://openalex.org/I100066346"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoralThesis"},{"id":"pmh:oai:figshare.com:article/27050764","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.18419/opus-3091","is_oa":true,"landing_page_url":"https://doi.org/10.18419/opus-3091","pdf_url":null,"source":{"id":"https://openalex.org/S7407052998","display_name":"Universit\u00e4tsbibliothek Stuttgart","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00286","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00286","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00286","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5801961956","display_name":null,"funder_award_id":"SFB 732","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320326275","display_name":"Higher Education Commision, Pakistan","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1508791843.pdf","grobid_xml":"https://content.openalex.org/works/W1508791843.grobid-xml"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W11511616","https://openalex.org/W12911848","https://openalex.org/W58590255","https://openalex.org/W58629251","https://openalex.org/W78623039","https://openalex.org/W222053410","https://openalex.org/W1487768769","https://openalex.org/W1489181569","https://openalex.org/W1551794154","https://openalex.org/W1561373746","https://openalex.org/W1597032530","https://openalex.org/W1607753411","https://openalex.org/W1631260214","https://openalex.org/W1636585317","https://openalex.org/W1683241483","https://openalex.org/W1916559533","https://openalex.org/W1973923101","https://openalex.org/W1982365650","https://openalex.org/W2006969979","https://openalex.org/W2007321142","https://openalex.org/W2009570821","https://openalex.org/W2019614587","https://openalex.org/W2024060665","https://openalex.org/W2038698865","https://openalex.org/W2049633694","https://openalex.org/W2056724340","https://openalex.org/W2075381214","https://openalex.org/W2086202918","https://openalex.org/W2090362702","https://openalex.org/W2090755665","https://openalex.org/W2096648470","https://openalex.org/W2097939100","https://openalex.org/W2102443632","https://openalex.org/W2109279255","https://openalex.org/W2110388853","https://openalex.org/W2113641473","https://openalex.org/W2118379766","https://openalex.org/W2118947254","https://openalex.org/W2119013622","https://openalex.org/W2119202242","https://openalex.org/W2124618303","https://openalex.org/W2125838338","https://openalex.org/W2127361019","https://openalex.org/W2138477841","https://openalex.org/W2138871615","https://openalex.org/W2139604620","https://openalex.org/W2139801634","https://openalex.org/W2140238877","https://openalex.org/W2140943754","https://openalex.org/W2142148293","https://openalex.org/W2142925167","https://openalex.org/W2146574666","https://openalex.org/W2146853049","https://openalex.org/W2148861208","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W2157136552","https://openalex.org/W2166202273","https://openalex.org/W2182117664","https://openalex.org/W2250943466","https://openalex.org/W2296656257","https://openalex.org/W2400050865","https://openalex.org/W2556053680","https://openalex.org/W2570451785","https://openalex.org/W2733017463","https://openalex.org/W2913739034","https://openalex.org/W3214348967"],"related_works":["https://openalex.org/W1539050421","https://openalex.org/W4307307996","https://openalex.org/W1563147278","https://openalex.org/W3162567751","https://openalex.org/W4285260836","https://openalex.org/W4221088574","https://openalex.org/W3094076422","https://openalex.org/W3046775127","https://openalex.org/W4220686584","https://openalex.org/W4319309271"],"abstract_inverted_index":{"We":[0,93],"present":[1],"a":[2,11,102],"generative":[3],"model":[4,25,47,72],"that":[5,126],"efficiently":[6],"mines":[7],"transliteration":[8,22,34,61,66,96,103,145],"pairs":[9,35,43,67,136],"in":[10,14,128],"consistent":[12],"fashion":[13],"three":[15,112],"different":[16],"settings:":[17],"unsupervised,":[18],"semi-supervised,":[19],"and":[20,36,68,107,123,157],"supervised":[21,124],"mining.":[23],"The":[24,46],"interpolates":[26],"two":[27,91],"sub-models,":[28],"one":[29,37],"for":[30,38],"the":[31,39,55,60,69,74,79,86,90,129],"generation":[32,40],"of":[33,41,89,114],"non-transliteration":[42,71],"(i.e.,":[44],"noise).":[45],"is":[48,82],"trained":[49],"on":[50,85,99,108],"noisy":[51],"unlabeled":[52,80],"data":[53,81,100],"using":[54],"EM":[56],"algorithm.":[57],"During":[58],"training":[59],"sub-model":[62],"learns":[63],"to":[64,151],"generate":[65],"fixed":[70],"generates":[73],"noise":[75],"pairs.":[76],"After":[77],"training,":[78],"disambiguated":[83],"based":[84],"posterior":[87],"probabilities":[88],"sub-models.":[92],"evaluate":[94],"our":[95,118,147],"mining":[97,104],"system":[98,119,148],"from":[101,138],"shared":[105,132],"task":[106],"parallel":[109,139],"corpora.":[110],"For":[111],"out":[113],"four":[115],"language":[116],"pairs,":[117,146],"outperforms":[120],"all":[121],"semi-supervised":[122],"systems":[125],"participated":[127],"NEWS":[130],"2010":[131],"task.":[133],"On":[134],"word":[135],"extracted":[137],"corpora":[140],"with":[141,154],"fewer":[142],"than":[143],"2%":[144],"achieves":[149],"up":[150],"86.7%":[152],"F-measure":[153],"77.9%":[155],"precision":[156],"97.8%":[158],"recall.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
