{"id":"https://openalex.org/W2119202242","doi":"https://doi.org/10.3115/v1/e14-4029","title":"Integrating an Unsupervised Transliteration Model into Statistical Machine Translation","display_name":"Integrating an Unsupervised Transliteration Model into Statistical Machine Translation","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2119202242","doi":"https://doi.org/10.3115/v1/e14-4029","mag":"2119202242"},"language":"en","primary_location":{"id":"doi:10.3115/v1/e14-4029","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-4029","pdf_url":"https://aclanthology.org/E14-4029.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 14th Conference of the European Chapter 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://aclanthology.org/E14-4029.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032689067","display_name":"Nadir Durrani","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Nadir Durrani","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042954793","display_name":"Hassan Sajjad","orcid":"https://orcid.org/0000-0002-8584-6595"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hassan Sajjad","raw_affiliation_strings":["Qatar Computing Research Institute","University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]},{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014808785","display_name":"Hieu Hoang","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hieu Hoang","raw_affiliation_strings":["University of Edinburgh","School of Informatics"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112315093","display_name":"Philipp Koehn","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philipp Koehn","raw_affiliation_strings":["University of Edinburgh","School of Informatics"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032689067"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":24.5246,"has_fulltext":true,"cited_by_count":89,"citation_normalized_percentile":{"value":0.9956622,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"153"},"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":0.9991000294685364,"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":0.9876999855041504,"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":0.9800869822502136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8614009618759155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7708135843276978},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7298675775527954},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.722449541091919},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4958232343196869},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49037766456604004},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.4839042127132416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3351440727710724}],"concepts":[{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.9800869822502136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8614009618759155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7708135843276978},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7298675775527954},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.722449541091919},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4958232343196869},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49037766456604004},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4839042127132416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3351440727710724},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/e14-4029","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-4029","pdf_url":"https://aclanthology.org/E14-4029.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 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.709.9497","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.709.9497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.qcri.qa/app/media/4873/","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/183240ba-da9f-41f5-b4dd-ed0442981f9f","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/183240ba-da9f-41f5-b4dd-ed0442981f9f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.3115/v1/e14-4029","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-4029","pdf_url":"https://aclanthology.org/E14-4029.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 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3829048491","display_name":null,"funder_award_id":"FP7/2007-2013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3911098002","display_name":"Bridges Across the Language Divide","funder_award_id":"287658","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3981126665","display_name":null,"funder_award_id":"Seventh Framework Programme","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5593277320","display_name":null,"funder_award_id":"2007-2013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5702163051","display_name":null,"funder_award_id":"FP7/2007","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2119202242.pdf","grobid_xml":"https://content.openalex.org/works/W2119202242.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W12911848","https://openalex.org/W78623039","https://openalex.org/W128271544","https://openalex.org/W170711724","https://openalex.org/W1551794154","https://openalex.org/W1628767011","https://openalex.org/W1893161951","https://openalex.org/W1968084137","https://openalex.org/W2075381214","https://openalex.org/W2101105183","https://openalex.org/W2107440414","https://openalex.org/W2110388853","https://openalex.org/W2114879013","https://openalex.org/W2117717100","https://openalex.org/W2124807415","https://openalex.org/W2134800885","https://openalex.org/W2135161317","https://openalex.org/W2136657878","https://openalex.org/W2138477841","https://openalex.org/W2139604620","https://openalex.org/W2146853049","https://openalex.org/W2150028966","https://openalex.org/W2156985047","https://openalex.org/W2157136552","https://openalex.org/W2159755860","https://openalex.org/W2161227214","https://openalex.org/W2163069610","https://openalex.org/W2166202273","https://openalex.org/W2170096403","https://openalex.org/W2184135559","https://openalex.org/W2250793660","https://openalex.org/W2250947781","https://openalex.org/W2257408573","https://openalex.org/W2270190199","https://openalex.org/W2293596968","https://openalex.org/W2595715041","https://openalex.org/W2917073205"],"related_works":["https://openalex.org/W4290878255","https://openalex.org/W4398154327","https://openalex.org/W4308540629","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2786253471","https://openalex.org/W2990400634","https://openalex.org/W3175595715","https://openalex.org/W6244059","https://openalex.org/W4293584592"],"abstract_inverted_index":{"We":[0,15,57],"investigate":[1],"three":[2],"methods":[3,40],"for":[4],"integrating":[5],"an":[6,11],"unsupervised":[7,34],"transliteration":[8,18,63,77],"model":[9,19],"into":[10],"end-to-end":[12],"SMT":[13],"system.":[14],"induce":[16],"a":[17],"from":[20,47],"parallel":[21],"data":[22],"and":[23,35,69],"use":[24],"it":[25],"to":[26,41,73],"translate":[27],"OOV":[28],"words.":[29],"Our":[30],"approach":[31],"is":[32],"fully":[33],"language":[36,55],"independent.":[37],"In":[38],"the":[39,74],"integrate":[42],"transliterations,":[43],"we":[44],"observed":[45],"improvements":[46],"0.23-0.75":[48],"(":[49],"0.41)":[50],"BLEU":[51],"points":[52],"across":[53],"7":[54],"pairs.":[56],"also":[58],"show":[59],"that":[60],"our":[61],"mined":[62],"corpora":[64],"provide":[65],"better":[66],"rule":[67],"coverage":[68],"translation":[70],"quality":[71],"compared":[72],"gold":[75],"standard":[76],"corpora.":[78]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":18},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
