{"id":"https://openalex.org/W2991020578","doi":"https://doi.org/10.26615/978-954-452-056-4_069","title":"Towards Functionally Similar Corpus Resources for Translation","display_name":"Towards Functionally Similar Corpus Resources for Translation","publication_year":2019,"publication_date":"2019-10-22","ids":{"openalex":"https://openalex.org/W2991020578","doi":"https://doi.org/10.26615/978-954-452-056-4_069","mag":"2991020578"},"language":"en","primary_location":{"id":"doi:10.26615/978-954-452-056-4_069","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_069","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_069","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.26615/978-954-452-056-4_069","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012912336","display_name":"Maria Kunilovskaya","orcid":"https://orcid.org/0000-0002-1473-4684"},"institutions":[{"id":"https://openalex.org/I3020440027","display_name":"University of Tyumen","ror":"https://ror.org/05vehv290","country_code":"RU","type":"education","lineage":["https://openalex.org/I3020440027"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Maria Kunilovskaya","raw_affiliation_strings":["University of Tyumen Tyumen, Russia"],"affiliations":[{"raw_affiliation_string":"University of Tyumen Tyumen, Russia","institution_ids":["https://openalex.org/I3020440027"]}]},{"author_position":"last","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 Leeds, UK"],"affiliations":[{"raw_affiliation_string":"University of Leeds Leeds, UK","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012912336"],"corresponding_institution_ids":["https://openalex.org/I3020440027"],"apc_list":null,"apc_paid":null,"fwci":0.1445,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6015786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"583","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T10759","display_name":"Translation Studies and Practices","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8157109022140503},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7071304321289062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.70139479637146},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.5957858562469482},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5591572523117065},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.546126663684845},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5414680242538452},{"id":"https://openalex.org/keywords/comparability","display_name":"Comparability","score":0.5301481485366821},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.47674688696861267},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.47423475980758667},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.44179484248161316},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43953824043273926},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4346836805343628},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20782777667045593},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10511523485183716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8157109022140503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7071304321289062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.70139479637146},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.5957858562469482},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5591572523117065},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.546126663684845},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5414680242538452},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.5301481485366821},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.47674688696861267},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.47423475980758667},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.44179484248161316},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43953824043273926},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4346836805343628},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20782777667045593},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10511523485183716},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26615/978-954-452-056-4_069","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_069","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_069","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.26615/978-954-452-056-4_069","is_oa":true,"landing_page_url":"http://doi.org/10.26615/978-954-452-056-4_069","pdf_url":"https://doi.org/10.26615/978-954-452-056-4_069","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings - Natural Language Processing in a Deep Learning World","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G5997868131","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321079","funder_display_name":"Russian Foundation for Basic Research"}],"funders":[{"id":"https://openalex.org/F4320321079","display_name":"Russian Foundation for Basic Research","ror":"https://ror.org/02mh1ke95"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2991020578.pdf","grobid_xml":"https://content.openalex.org/works/W2991020578.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W21004162","https://openalex.org/W146117928","https://openalex.org/W646294924","https://openalex.org/W1522301498","https://openalex.org/W2008959343","https://openalex.org/W2019413183","https://openalex.org/W2057800147","https://openalex.org/W2062837929","https://openalex.org/W2114097960","https://openalex.org/W2138069620","https://openalex.org/W2148959489","https://openalex.org/W2155870214","https://openalex.org/W2170571488","https://openalex.org/W2175972206","https://openalex.org/W2198750770","https://openalex.org/W2250680310","https://openalex.org/W2395452408","https://openalex.org/W2498287611","https://openalex.org/W2501489186","https://openalex.org/W2736989307","https://openalex.org/W2749945937","https://openalex.org/W2782838522","https://openalex.org/W2783822311","https://openalex.org/W2795582519","https://openalex.org/W2798689286","https://openalex.org/W2916814906","https://openalex.org/W2964121744","https://openalex.org/W3209447568","https://openalex.org/W4206365372"],"related_works":["https://openalex.org/W2365594754","https://openalex.org/W2575292835","https://openalex.org/W4287902769","https://openalex.org/W3001140700","https://openalex.org/W2995453361","https://openalex.org/W3021704418","https://openalex.org/W4390295458","https://openalex.org/W3152052241","https://openalex.org/W3175595715","https://openalex.org/W2006337894"],"abstract_inverted_index":{"The":[0],"paper":[1],"describes":[2],"a":[3,21,26,44,47,142,150],"computational":[4],"approach":[5],"to":[6,32,58,90,126],"produce":[7],"functionally":[8,64,128],"comparable":[9],"monolingual":[10],"corpus":[11],"resources":[12],"for":[13,72,145,154],"translation":[14],"studies":[15],"and":[16,82,119,122],"contrastive":[17],"analysis.":[18],"We":[19],"exploit":[20],"text-external":[22],"approach,":[23],"based":[24,77],"on":[25,78],"set":[27],"of":[28,50,63,94,108],"Functional":[29,138],"Text":[30,139],"Dimensions":[31,140],"model":[33],"text":[34,39,51,74,146],"functions,":[35],"so":[36],"that":[37,136],"each":[38],"can":[40,55],"be":[41,56],"represented":[42],"as":[43,99],"vector":[45],"in":[46,131],"multidimensional":[48],"space":[49],"functions.":[52,158],"These":[53],"vectors":[54],"used":[57],"find":[59],"reasonably":[60],"homogeneous":[61],"subsets":[62],"similar":[65,129],"texts":[66,155],"across":[67],"different":[68],"corpora.":[69],"Our":[70,133],"models":[71,125],"predicting":[73],"functions":[75],"are":[76],"recurrent":[79],"neural":[80],"networks":[81],"traditional":[83],"feature-based":[84],"machine":[85],"learning":[86],"approaches.":[87],"In":[88],"addition":[89],"using":[91],"the":[92,95,105,109,113,137],"categories":[93],"British":[96],"National":[97],"Corpus":[98],"our":[100,124],"test":[101],"case,":[102],"we":[103],"investigated":[104],"functional":[106],"comparability":[107],"English":[110],"parts":[111],"from":[112],"two":[114],"parallel":[115],"corpora:":[116],"CroCo":[117],"(English-German)":[118],"RusLTC":[120],"(English-Russian)":[121],"applied":[123],"define":[127],"clusters":[130],"them.":[132],"results":[134],"show":[135],"provide":[141],"useful":[143],"description":[144],"categories,":[147],"while":[148],"allowing":[149],"more":[151],"flexible":[152],"representation":[153],"with":[156],"hybrid":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-12-05T00:00:00"}