{"id":"https://openalex.org/W2422372688","doi":"https://doi.org/10.1017/s1351324916000115","title":"Recent advances in machine translation using comparable corpora","display_name":"Recent advances in machine translation using comparable corpora","publication_year":2016,"publication_date":"2016-06-15","ids":{"openalex":"https://openalex.org/W2422372688","doi":"https://doi.org/10.1017/s1351324916000115","mag":"2422372688"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324916000115","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324916000115","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/AD075A1D621AC2B687C822FEB642561A/S1351324916000115a.pdf/div-class-title-recent-advances-in-machine-translation-using-comparable-corpora-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/AD075A1D621AC2B687C822FEB642561A/S1351324916000115a.pdf/div-class-title-recent-advances-in-machine-translation-using-comparable-corpora-div.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049674705","display_name":"Reinhard Rapp","orcid":"https://orcid.org/0000-0002-7245-551X"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"REINHARD RAPP","raw_affiliation_strings":["University of Mainz e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mainz e-mail:","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072701587","display_name":"Serge Sharoff","orcid":"https://orcid.org/0000-0002-4877-0210"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"SERGE SHAROFF","raw_affiliation_strings":["University of Leeds e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leeds e-mail:","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090195478","display_name":"Pierre Zweigenbaum","orcid":"https://orcid.org/0000-0001-8410-4808"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"PIERRE ZWEIGENBAUM","raw_affiliation_strings":["LIMSI, CNRS, Universit\u00e9 Paris-Saclay e-mail:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIMSI, CNRS, Universit\u00e9 Paris-Saclay e-mail:","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I4210115485"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3249,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86990804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"22","issue":"4","first_page":"501","last_page":"516"},"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9287011623382568},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7806154489517212},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7305538654327393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.676964521408081},{"id":"https://openalex.org/keywords/comparability","display_name":"Comparability","score":0.6632956266403198},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.6055945158004761},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5957893133163452},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5841324329376221},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5417969226837158},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.539908230304718},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4269689917564392},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10001429915428162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9287011623382568},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7806154489517212},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7305538654327393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.676964521408081},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.6632956266403198},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.6055945158004761},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5957893133163452},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5841324329376221},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5417969226837158},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.539908230304718},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4269689917564392},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10001429915428162},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324916000115","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324916000115","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/AD075A1D621AC2B687C822FEB642561A/S1351324916000115a.pdf/div-class-title-recent-advances-in-machine-translation-using-comparable-corpora-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1017/s1351324916000115","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324916000115","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/AD075A1D621AC2B687C822FEB642561A/S1351324916000115a.pdf/div-class-title-recent-advances-in-machine-translation-using-comparable-corpora-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2422372688.pdf","grobid_xml":"https://content.openalex.org/works/W2422372688.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W108460122","https://openalex.org/W141732386","https://openalex.org/W342285082","https://openalex.org/W614252839","https://openalex.org/W1543317902","https://openalex.org/W1570490112","https://openalex.org/W1614298861","https://openalex.org/W1749198638","https://openalex.org/W1818534184","https://openalex.org/W1828724394","https://openalex.org/W1914743126","https://openalex.org/W1964922004","https://openalex.org/W1973152633","https://openalex.org/W2057867321","https://openalex.org/W2061118075","https://openalex.org/W2097766966","https://openalex.org/W2102749417","https://openalex.org/W2107695330","https://openalex.org/W2117198860","https://openalex.org/W2118090838","https://openalex.org/W2118606687","https://openalex.org/W2120779048","https://openalex.org/W2121745180","https://openalex.org/W2123595463","https://openalex.org/W2126725946","https://openalex.org/W2139812240","https://openalex.org/W2140406733","https://openalex.org/W2140903445","https://openalex.org/W2158199200","https://openalex.org/W2164746297","https://openalex.org/W2176802839","https://openalex.org/W2237260780","https://openalex.org/W2250288378","https://openalex.org/W2250600644","https://openalex.org/W2251013614","https://openalex.org/W2251033195","https://openalex.org/W2251257851","https://openalex.org/W2251345617","https://openalex.org/W2251352461","https://openalex.org/W2251631381","https://openalex.org/W2277589743","https://openalex.org/W2486220227","https://openalex.org/W2950577311","https://openalex.org/W2950682695","https://openalex.org/W4322490533","https://openalex.org/W6637647663","https://openalex.org/W6814405609"],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2786253471","https://openalex.org/W3175595715","https://openalex.org/W4298129735","https://openalex.org/W2604275745","https://openalex.org/W2986030184","https://openalex.org/W2104907655","https://openalex.org/W2985215540","https://openalex.org/W4307459710","https://openalex.org/W3155572818"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2,78],"highlights":[3],"some":[4],"of":[5,12,24,33,76,97,114],"the":[6,10,77,95,109,112],"recent":[7,116],"developments":[8],"in":[9],"field":[11],"machine":[13,84],"translation":[14,85],"using":[15,86],"comparable":[16,25,72,87,101],"corpora.":[17,73,102],"We":[18],"start":[19],"by":[20],"updating":[21],"previous":[22],"definitions":[23],"corpora":[26],"and":[27,111],"then":[28],"look":[29],"at":[30,83],"bilingual":[31],"versions":[32],"continuous":[34],"vector":[35],"space":[36],"models.":[37],"Recently,":[38],"neural":[39],"networks":[40],"have":[41],"been":[42],"used":[43],"to":[44,67,71],"obtain":[45],"latent":[46],"context":[47],"representations":[48],"with":[49,94],"only":[50,64],"few":[51],"dimensions":[52],"which":[53],"are":[54],"often":[55],"called":[56],"word":[57],"embeddings.":[58],"These":[59],"promising":[60],"new":[61],"techniques":[62],"cannot":[63],"be":[65],"applied":[66],"parallel":[68,98],"but":[69],"also":[70],"Subsequent":[74],"sections":[75],"discuss":[79],"work":[80,92],"specifically":[81],"targeting":[82],"corpora,":[88],"as":[89,91],"well":[90],"dealing":[93],"extraction":[96],"segments":[99],"from":[100],"Finally,":[103],"we":[104],"give":[105],"an":[106],"overview":[107],"on":[108,119],"design":[110],"results":[113],"a":[115],"shared":[117],"task":[118],"measuring":[120],"document":[121],"comparability":[122],"across":[123],"languages.":[124]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
