{"id":"https://openalex.org/W2609278920","doi":"https://doi.org/10.1109/jstsp.2017.2764273","title":"An Empirical Analysis of NMT-Derived Interlingual Embeddings and Their Use in Parallel Sentence Identification","display_name":"An Empirical Analysis of NMT-Derived Interlingual Embeddings and Their Use in Parallel Sentence Identification","publication_year":2017,"publication_date":"2017-10-18","ids":{"openalex":"https://openalex.org/W2609278920","doi":"https://doi.org/10.1109/jstsp.2017.2764273","mag":"2609278920"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2017.2764273","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2764273","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/jstsp.2017.2764273","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029540488","display_name":"Cristina Espa\u00f1a-Bonet","orcid":"https://orcid.org/0000-0001-5414-4710"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cristina Espana-Bonet","raw_affiliation_strings":["DFKI, and the University of Saarland, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5414-4710","affiliations":[{"raw_affiliation_string":"DFKI, and the University of Saarland, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040527076","display_name":"\u00c1d\u00e1m Varga","orcid":"https://orcid.org/0000-0002-7564-2054"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adam Csaba Varga","raw_affiliation_strings":["University of Saarland, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7564-2054","affiliations":[{"raw_affiliation_string":"University of Saarland, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067489760","display_name":"Alberto Barr\u00f3n\u2010Cede\u00f1o","orcid":"https://orcid.org/0000-0003-4719-3420"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Alberto Barron-Cedeno","raw_affiliation_strings":["Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Hamad Bin Khalifa University, Doha, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049194403","display_name":"Josef van Genabith","orcid":"https://orcid.org/0000-0003-1322-7944"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Josef van Genabith","raw_affiliation_strings":["DFKI, and the University of Saarland, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI, and the University of Saarland, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.3647,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.98702082,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"11","issue":"8","first_page":"1340","last_page":"1350"},"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":0.9998999834060669,"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":0.9939000010490417,"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":0.8589175939559937},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8347357511520386},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7338286638259888},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.725119948387146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6831449866294861},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6088427901268005},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6045090556144714},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5368623733520508},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5031465888023376},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5009350776672363},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4936746060848236},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47062185406684875},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.45337599515914917},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.4381740093231201},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4195401966571808},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09354603290557861},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08972123265266418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8589175939559937},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8347357511520386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7338286638259888},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.725119948387146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6831449866294861},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6088427901268005},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6045090556144714},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5368623733520508},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5031465888023376},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5009350776672363},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4936746060848236},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47062185406684875},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.45337599515914917},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.4381740093231201},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4195401966571808},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09354603290557861},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08972123265266418},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/jstsp.2017.2764273","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2764273","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1704.05415","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.05415","pdf_url":"https://arxiv.org/pdf/1704.05415","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:cris.unibo.it:11585/707811","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/document/8070942","pdf_url":"http://hdl.handle.net/11585/707811","source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:figshare.com:article/27082699","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/An_Empirical_Analysis_of_NMT-Derived_Interlingual_Embeddings_and_Their_Use_in_Parallel_Sentence_Identification/27082699","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1109/jstsp.2017.2764273","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2764273","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W53720638","https://openalex.org/W131533222","https://openalex.org/W342285082","https://openalex.org/W635530177","https://openalex.org/W1543107604","https://openalex.org/W1544505227","https://openalex.org/W1574901103","https://openalex.org/W1614298861","https://openalex.org/W1753482797","https://openalex.org/W1869906767","https://openalex.org/W1875842236","https://openalex.org/W1964162497","https://openalex.org/W1980813323","https://openalex.org/W2028776121","https://openalex.org/W2029097226","https://openalex.org/W2107695330","https://openalex.org/W2126725946","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2250539671","https://openalex.org/W2250816155","https://openalex.org/W2251395010","https://openalex.org/W2251463950","https://openalex.org/W2251743902","https://openalex.org/W2460354904","https://openalex.org/W2512924740","https://openalex.org/W2531207078","https://openalex.org/W2550821151","https://openalex.org/W2555745756","https://openalex.org/W2594229957","https://openalex.org/W2739533097","https://openalex.org/W2742155240","https://openalex.org/W2760656271","https://openalex.org/W2915311057","https://openalex.org/W2962784628","https://openalex.org/W2963247703","https://openalex.org/W2963672008","https://openalex.org/W2963756346","https://openalex.org/W2963842982","https://openalex.org/W2964034111","https://openalex.org/W2964308564","https://openalex.org/W3104033643","https://openalex.org/W3140009346","https://openalex.org/W4237394013","https://openalex.org/W4302343710","https://openalex.org/W4313908941","https://openalex.org/W6600880057","https://openalex.org/W6605323724","https://openalex.org/W6632555176","https://openalex.org/W6632640022","https://openalex.org/W6636510571","https://openalex.org/W6637698695","https://openalex.org/W6638920771","https://openalex.org/W6679155404","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6684025965","https://openalex.org/W6685145238","https://openalex.org/W6691329832","https://openalex.org/W6691351334","https://openalex.org/W6691525129","https://openalex.org/W6719018595","https://openalex.org/W6729684557","https://openalex.org/W6742080785","https://openalex.org/W6786240170"],"related_works":["https://openalex.org/W2786253471","https://openalex.org/W3175595715","https://openalex.org/W2797913374","https://openalex.org/W2604275745","https://openalex.org/W4293584592","https://openalex.org/W2986030184","https://openalex.org/W2104907655","https://openalex.org/W4287212313","https://openalex.org/W2985215540","https://openalex.org/W4307459710"],"abstract_inverted_index":{"End-to-end":[0],"neural":[1,30,104],"machine":[2,7,105],"translation":[3,8,12,106],"has":[4],"overtaken":[5],"statistical":[6],"in":[9,78,158],"terms":[10],"of":[11,23,69,88,93,112,122,150],"quality":[13,128],"for":[14],"some":[15],"language":[16],"pairs,":[17],"specially":[18],"those":[19],"with":[20,184],"large":[21],"amounts":[22],"parallel":[24,156],"data.":[25],"Besides":[26],"this":[27],"palpable":[28],"improvement,":[29],"networks":[31],"provide":[32],"several":[33],"new":[34,66],"properties.":[35],"A":[36],"single":[37],"system":[38],"can":[39],"be":[40],"trained":[41],"to":[42],"translate":[43],"between":[44],"many":[45],"languages":[46],"at":[47],"almost":[48],"no":[49],"additional":[50],"cost":[51],"other":[52],"than":[53],"training":[54],"time.":[55],"Furthermore,":[56],"internal":[57],"representations":[58],"learned":[59,77],"by":[60,131],"the":[61,91,94,103,113,151],"network":[62],"serve":[63],"as":[64,118,136,138,147],"a":[65,123,171],"semantic":[67],"representation":[68,121],"words-or":[70],"sentences-which,":[71],"unlike":[72],"standard":[73],"word":[74],"embeddings,":[75],"are":[76],"an":[79,119,162],"essentially":[80],"bilingual":[81],"or":[82],"even":[83],"multilingual":[84],"context.":[85],"In":[86],"view":[87],"these":[89],"properties,":[90],"contribution":[92],"present":[95],"paper":[96],"is":[97],"twofold.":[98],"First,":[99],"we":[100,154],"systematically":[101],"study":[102],"(NMT)":[107],"context":[108,178,181],"vectors,":[109],"i.e.,":[110],"output":[111],"encoder,":[114],"and":[115,129,141],"their":[116,127],"power":[117],"interlingua":[120],"sentence.":[124],"We":[125],"assess":[126],"effectiveness":[130],"measuring":[132],"similarities":[133],"across":[134],"translations,":[135],"well":[137],"semantically":[139,142],"related":[140],"unrelated":[143],"sentence":[144],"pairs.":[145],"Second,":[146],"extrinsic":[148],"evaluation":[149],"first":[152],"point,":[153],"identify":[155],"sentences":[157],"comparable":[159],"corpora,":[160],"obtaining":[161],"F":[163,187],"<sub":[164,188],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[165,189],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sub>":[166,190],"=98.2%":[167],"on":[168],"data":[169],"from":[170],"shared":[172],"task":[173],"when":[174],"using":[175],"only":[176],"NMT":[177],"vectors.":[179],"Using":[180],"vectors":[182],"jointly":[183],"similarity":[185],"measures":[186],"reaches":[191],"98.9%.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2017-05-05T00:00:00"}