{"id":"https://openalex.org/W2426200316","doi":"https://doi.org/10.1017/s1351324916000140","title":"Exploiting unbalanced specialized comparable corpora for bilingual lexicon extraction","display_name":"Exploiting unbalanced specialized comparable corpora for bilingual lexicon extraction","publication_year":2016,"publication_date":"2016-06-15","ids":{"openalex":"https://openalex.org/W2426200316","doi":"https://doi.org/10.1017/s1351324916000140","mag":"2426200316"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324916000140","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324916000140","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018688029","display_name":"Emmanuel Morin","orcid":"https://orcid.org/0000-0001-8208-7039"},"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/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"EMMANUEL MORIN","raw_affiliation_strings":["Universit\u00e9 de Nantes, LINA UMR CNRS 6241, 2 rue de la houssini\u00e8re, BP 92208, 44322 Nantes Cedex 03, France e-mails:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Nantes, LINA UMR CNRS 6241, 2 rue de la houssini\u00e8re, BP 92208, 44322 Nantes Cedex 03, France e-mails:","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I97188460"]}]},{"author_position":"last","author":{"id":null,"display_name":"AMIR HAZEM","orcid":null},"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/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"AMIR HAZEM","raw_affiliation_strings":["Universit\u00e9 de Nantes, LINA UMR CNRS 6241, 2 rue de la houssini\u00e8re, BP 92208, 44322 Nantes Cedex 03, France e-mails:"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Nantes, LINA UMR CNRS 6241, 2 rue de la houssini\u00e8re, BP 92208, 44322 Nantes Cedex 03, France e-mails:","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I97188460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1945,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91301189,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"22","issue":"4","first_page":"575","last_page":"601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6938999891281128,"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":0.6938999891281128,"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":0.06400000303983688,"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"}},{"id":"https://openalex.org/T12881","display_name":"linguistics and terminology studies","score":0.0551999993622303,"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":0.8261272311210632},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7599977254867554},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6857289671897888},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6521698236465454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6485439538955688},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6225565671920776},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.5895493030548096},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5826770067214966},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.5488751530647278},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.471090167760849},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20621684193611145},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07138761878013611},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.058288902044296265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8261272311210632},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7599977254867554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6857289671897888},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6521698236465454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6485439538955688},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6225565671920776},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5895493030548096},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5826770067214966},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.5488751530647278},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.471090167760849},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20621684193611145},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07138761878013611},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.058288902044296265},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s1351324916000140","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324916000140","pdf_url":null,"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"},{"id":"pmh:oai:HAL:hal-01188579v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01188579","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Natural Language Engineering, 2016, Special Issue: Machine Translation Using Comparable Corpora, pp.27","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5241710187","display_name":"Knowledge Rrich Context for Terminology Translation","funder_award_id":"ANR-12-CORD-0020","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W89131023","https://openalex.org/W95136384","https://openalex.org/W135528467","https://openalex.org/W1482316958","https://openalex.org/W1493790738","https://openalex.org/W1549114989","https://openalex.org/W1570490112","https://openalex.org/W1582850894","https://openalex.org/W1590839732","https://openalex.org/W1597533204","https://openalex.org/W1626233182","https://openalex.org/W1889220380","https://openalex.org/W1934041838","https://openalex.org/W1973550659","https://openalex.org/W1979346010","https://openalex.org/W2011248508","https://openalex.org/W2022597264","https://openalex.org/W2024732135","https://openalex.org/W2034274945","https://openalex.org/W2039857374","https://openalex.org/W2082092506","https://openalex.org/W2084988910","https://openalex.org/W2102749417","https://openalex.org/W2121415745","https://openalex.org/W2133837072","https://openalex.org/W2134237567","https://openalex.org/W2138575863","https://openalex.org/W2154558620","https://openalex.org/W2158195707","https://openalex.org/W2162967019","https://openalex.org/W2163953154","https://openalex.org/W2167265720","https://openalex.org/W2168820179","https://openalex.org/W2250332852","https://openalex.org/W2250362383","https://openalex.org/W2251413422","https://openalex.org/W2251914791","https://openalex.org/W2588710172","https://openalex.org/W2900926741","https://openalex.org/W3203627005","https://openalex.org/W4213009331","https://openalex.org/W6677145740"],"related_works":["https://openalex.org/W3048269104","https://openalex.org/W2617430858","https://openalex.org/W2010503965","https://openalex.org/W3091429835","https://openalex.org/W4297097224","https://openalex.org/W2122691642","https://openalex.org/W2296152660","https://openalex.org/W3024381485","https://openalex.org/W2394602299","https://openalex.org/W4295267149"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"main":[2],"work":[3],"in":[4,21,130,134],"bilingual":[5,66],"lexicon":[6],"extraction":[7,68],"from":[8],"comparable":[9,42,59,116,127],"corpora":[10,18,60,128],"is":[11,31,90],"based":[12],"on":[13,53,62],"the":[14,26,35,41,54,63,80,100,110,122,135],"implicit":[15],"hypothesis":[16],"that":[17,98,121],"are":[19,106],"balanced":[20],"terms":[22],"of":[23,37,40,56,65,102,113,124,137],"size.":[24],"However,":[25],"historical":[27],"context-based":[28,81],"projection":[29,82],"method":[30,83],"relatively":[32],"insensitive":[33],"to":[34,84],"size":[36],"each":[38],"part":[39,112],"corpus.":[43,117],"Within":[44],"this":[45],"context,":[46],"we":[47,74],"have":[48,75],"carried":[49],"out":[50],"a":[51,77,131],"study":[52],"influence":[55],"unbalanced":[57,115,125],"specialized":[58,126],"and":[61],"quality":[64,136],"terminology":[67],"by":[69,92],"doing":[70],"different":[71],"experiments.":[72],"Moreover,":[73],"introduced":[76],"strategy":[78],"into":[79],"re-estimate":[85],"word":[86,103],"co-occurrence":[87],"observations.":[88],"This":[89],"done":[91],"using":[93],"smoothing":[94],"or":[95],"prediction":[96],"techniques":[97],"boost":[99],"observations":[101],"co-occurrences":[104],"which":[105],"mainly":[107],"useful":[108],"for":[109],"smallest":[111],"an":[114],"Our":[118],"results":[119,129],"show":[120],"use":[123],"significant":[132],"improvement":[133],"extracted":[138],"lexicons.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
