{"id":"https://openalex.org/W61749939","doi":"https://doi.org/10.63317/5b4rq3qiukg3","title":"A Python Toolkit for Universal Transliteration","display_name":"A Python Toolkit for Universal Transliteration","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W61749939","doi":"https://doi.org/10.63317/5b4rq3qiukg3","mag":"61749939"},"language":"en","primary_location":{"id":"doi:10.63317/5b4rq3qiukg3","doi":"https://doi.org/10.63317/5b4rq3qiukg3","is_oa":true,"landing_page_url":"https://doi.org/10.63317/5b4rq3qiukg3","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/30_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/30_Paper.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043567153","display_name":"Ting Qian","orcid":"https://orcid.org/0000-0001-6113-0341","observed_orcids":["https://orcid.org/0000-0001-6113-0341","https://orcid.org/0000-0001-5872-7024"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Qian","raw_affiliation_strings":["University of Rochester 1 , OHSU 2 , ETS 3 ,","University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester 1 , OHSU 2 , ETS 3 ,","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043447750","display_name":"Kristy Hollingshead","orcid":"https://orcid.org/0000-0002-4900-0517","observed_orcids":["https://orcid.org/0000-0002-4900-0517"]},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]},{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristy Hollingshead","raw_affiliation_strings":["University of Rochester 1 , OHSU 2 , ETS 3 ,","Oregon Health and Science University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester 1 , OHSU 2 , ETS 3 ,","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Oregon Health and Science University","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110299354","display_name":"Su Youn Yoon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Su-youn Yoon","raw_affiliation_strings":["University of Rochester 1 , OHSU 2 , ETS 3 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester 1 , OHSU 2 , ETS 3 ,","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024935414","display_name":"Kyoung Young Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyoung-young Kim","raw_affiliation_strings":["University of Rochester 1 , OHSU 2 , ETS 3 ,","UIUC#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester 1 , OHSU 2 , ETS 3 ,","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"UIUC#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063612469","display_name":"Richard Sproat","orcid":"https://orcid.org/0000-0002-9040-5196","observed_orcids":["https://orcid.org/0000-0002-9040-5196"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Sproat","raw_affiliation_strings":["UIUC 4 , OHSU","Oregon Health and Science University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UIUC 4 , OHSU","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I165690674"]},{"raw_affiliation_string":"Oregon Health and Science University","institution_ids":["https://openalex.org/I165690674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.00572106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":92,"max":98},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T10201","display_name":"Speech Recognition and Synthesis","score":9.999999747378752e-05,"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/transliteration","display_name":"transliteration","score":0.9509999752044678},{"id":"https://openalex.org/keywords/comparable-corpora","display_name":"comparable corpora","score":0.8650000095367432},{"id":"https://openalex.org/keywords/multilingual-text-mining","display_name":"multilingual text mining","score":0.7630000114440918},{"id":"https://openalex.org/keywords/term-extraction","display_name":"term extraction","score":0.531000018119812},{"id":"https://openalex.org/keywords/phonetic-similarity","display_name":"phonetic similarity","score":0.765999972820282},{"id":"https://openalex.org/keywords/temporal-measures","display_name":"temporal measures","score":0.6869999766349792},{"id":"https://openalex.org/keywords/python-library","display_name":"Python library","score":0.7039999961853027},{"id":"https://openalex.org/keywords/natural-language-processing-toolkit","display_name":"natural language processing toolkit","score":0.5189999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8844943046569824},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.8715640306472778},{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.839673638343811},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8211989402770996},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7851557731628418},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.675945520401001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5698909759521484},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5535931587219238},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4554232954978943},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.4191519320011139},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3315905034542084},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.21000534296035767}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.63317/5b4rq3qiukg3","doi":"https://doi.org/10.63317/5b4rq3qiukg3","is_oa":true,"landing_page_url":"https://doi.org/10.63317/5b4rq3qiukg3","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/30_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.5695","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.5695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/30_Paper.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.63317/5b4rq3qiukg3","doi":"https://doi.org/10.63317/5b4rq3qiukg3","is_oa":true,"landing_page_url":"https://doi.org/10.63317/5b4rq3qiukg3","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2010/pdf/30_Paper.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8997096563","display_name":"RI: Cross-Cutting Research Workshops in Intelligent Information Systems","funder_award_id":"0705708","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"},{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W61749939.pdf","grobid_xml":"https://content.openalex.org/works/W61749939.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1878590289","https://openalex.org/W2096648470","https://openalex.org/W2117408078","https://openalex.org/W2119013622","https://openalex.org/W2127361019","https://openalex.org/W2143017621","https://openalex.org/W2953320089"],"related_works":["https://openalex.org/W3166486483","https://openalex.org/W2994192584","https://openalex.org/W2166663858","https://openalex.org/W2157136552","https://openalex.org/W1762503104","https://openalex.org/W7099557599","https://openalex.org/W7100148544","https://openalex.org/W625002222","https://openalex.org/W2250930967","https://openalex.org/W7104511848"],"abstract_inverted_index":{"We":[0],"describe":[1],"ScriptTranscriber,":[2],"an":[3,90,125],"open":[4,126],"source":[5,127,156],"toolkit":[6],"for":[7,23,32,41,103,109,131,143],"extracting":[8,24],"transliterations":[9,47,95],"in":[10,16,59,79],"comparable":[11,73,98],"corpora":[12],"from":[13,29,96],"languages":[14,83],"written":[15],"different":[17,86],"scripts.The":[18],"system":[19,54],"includes":[20],"various":[21],"methods":[22],"potential":[25],"terms":[26],"of":[27,38,82,134,152],"interest":[28],"raw":[30],"text,":[31,78],"providing":[33],"guesses":[34],"on":[35],"the":[36,60,97,153],"pronunciations":[37],"terms,":[39],"and":[40,51,65,114],"comparing":[42],"two":[43],"strings":[44],"as":[45,76,150],"possible":[46],"using":[48],"both":[49],"phonetic":[50],"temporal":[52],"measures.The":[53],"works":[55],"with":[56],"any":[57],"script":[58],"Unicode":[61],"Basic":[62],"Multilingual":[63],"Plane":[64],"is":[66,100,117,148],"easily":[67],"extended":[68],"to":[69,93,120],"include":[70],"new":[71],"modules.Given":[72],"corpora,":[74],"such":[75],"newswire":[77],"a":[80,139,144],"pair":[81],"that":[84,129],"use":[85],"scripts,":[87],"ScriptTranscriber":[88],"provides":[89,124],"easy":[91],"way":[92],"mine":[94],"texts.This":[99],"particularly":[101],"useful":[102],"underresourced":[104],"languages,":[105],"where":[106,115],"training":[107],"data":[108],"transliteration":[110,141],"may":[111],"be":[112],"lacking,":[113],"it":[116],"thus":[118],"hard":[119],"train":[121],"good":[122],"transliterators.ScriptTranscriber":[123],"package":[128],"allows":[130],"ready":[132],"incorporation":[133],"more":[135],"sophisticated":[136],"modules":[137],"-e.g.":[138],"trained":[140],"model":[142],"particular":[145],"language":[146],"pair.ScriptTranscriber":[147],"available":[149],"part":[151],"nltk":[154],"contrib":[155],"tree":[157],"at":[158],"http://code.google.com/p/nltk/.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}
