{"id":"https://openalex.org/W2250332852","doi":"https://doi.org/10.3115/v1/p14-1121","title":"Looking at Unbalanced Specialized Comparable Corpora for Bilingual Lexicon Extraction","display_name":"Looking at Unbalanced Specialized Comparable Corpora for Bilingual Lexicon Extraction","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250332852","doi":"https://doi.org/10.3115/v1/p14-1121","mag":"2250332852"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-1121","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/p14-1121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","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/I4210117005","display_name":"Laboratoire des Sciences du Num\u00e9rique de Nantes","ror":"https://ror.org/02snf8m58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100445878","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210117005","https://openalex.org/I4210124215","https://openalex.org/I4210127572","https://openalex.org/I4210139971","https://openalex.org/I97188460","https://openalex.org/I97188460"]},{"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":["LS2N - \u00e9quipe TALN   - Traitement Automatique du Langage Naturel (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LS2N - \u00e9quipe TALN   - Traitement Automatique du Langage Naturel (France)","institution_ids":["https://openalex.org/I4210117005","https://openalex.org/I97188460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112027771","display_name":"Amir Hazem","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165258","display_name":"Laboratoire d'informatique de Nantes Atlantique","ror":"https://ror.org/05487pd16","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I4210165258","https://openalex.org/I97188460"]},{"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":["LINA - Laboratoire d'Informatique de Nantes Atlantique (LINA - Facult\u00e9 des Sciences 2 rue de la Houssini\u00e8re - BP 92208 44322 NANTES CEDEX 3 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINA - Laboratoire d'Informatique de Nantes Atlantique (LINA - Facult\u00e9 des Sciences 2 rue de la Houssini\u00e8re - BP 92208 44322 NANTES CEDEX 3 - France)","institution_ids":["https://openalex.org/I4210165258","https://openalex.org/I97188460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1284","last_page":"1293"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9937000274658203,"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":0.989300012588501,"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":0.8650055527687073},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7740668058395386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7195695638656616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.705113410949707},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6367129683494568},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.5884351134300232},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5628465414047241},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.5626829862594604},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5059253573417664},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44362419843673706},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4289216995239258},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1447199285030365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8650055527687073},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7740668058395386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7195695638656616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.705113410949707},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6367129683494568},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.5884351134300232},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5628465414047241},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.5626829862594604},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5059253573417664},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44362419843673706},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4289216995239258},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1447199285030365},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/p14-1121","is_oa":false,"landing_page_url":"https://doi.org/10.3115/v1/p14-1121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":null,"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":30,"referenced_works":["https://openalex.org/W71111251","https://openalex.org/W89131023","https://openalex.org/W135528467","https://openalex.org/W148254311","https://openalex.org/W1498892495","https://openalex.org/W1532325895","https://openalex.org/W1570490112","https://openalex.org/W1582850894","https://openalex.org/W1590839732","https://openalex.org/W1626233182","https://openalex.org/W1889220380","https://openalex.org/W1972871876","https://openalex.org/W1987840996","https://openalex.org/W1988012253","https://openalex.org/W2011248508","https://openalex.org/W2084988910","https://openalex.org/W2102749417","https://openalex.org/W2113794846","https://openalex.org/W2118606687","https://openalex.org/W2121415745","https://openalex.org/W2133837072","https://openalex.org/W2138575863","https://openalex.org/W2154558620","https://openalex.org/W2162967019","https://openalex.org/W2167265720","https://openalex.org/W2168820179","https://openalex.org/W2250362383","https://openalex.org/W2251413422","https://openalex.org/W2403863882","https://openalex.org/W3203627005"],"related_works":["https://openalex.org/W2350593162","https://openalex.org/W2390350206","https://openalex.org/W1969477129","https://openalex.org/W2921208823","https://openalex.org/W2353483812","https://openalex.org/W2131808775","https://openalex.org/W2130038259","https://openalex.org/W2360756181","https://openalex.org/W2374093222","https://openalex.org/W3048269104"],"abstract_inverted_index":{"The":[0],"main":[1],"work":[2],"in":[3,85,105],"bilingual":[4,64],"lexicon":[5],"extraction":[6,66],"from":[7],"comparable":[8,41,58,99],"corpora":[9,17,59,100],"is":[10,30],"based":[11],"on":[12,52,60],"the":[13,21,34,40,53,61,79,86,94,106],"implicit":[14],"hypothesis":[15],"that":[16,77,93],"are":[18],"balanced.":[19],"However,":[20],"historical":[22],"contextbased":[23],"projection":[24,88],"method":[25],"dedicated":[26],"to":[27,33],"this":[28,44],"task":[29],"relatively":[31],"insensitive":[32],"sizes":[35],"of":[36,39,55,63,81,96,108],"each":[37],"part":[38],"corpus.":[42],"Within":[43],"context,":[45],"we":[46,71],"have":[47,72],"carried":[48],"out":[49],"a":[50,74,102],"study":[51],"influence":[54],"unbalanced":[56,97],"specialized":[57,98],"quality":[62,107],"terminology":[65],"through":[67],"different":[68],"experiments.":[69],"Moreover,":[70],"introduced":[73],"regression":[75],"model":[76],"boosts":[78],"observations":[80],"word":[82],"cooccurrences":[83],"used":[84],"context-based":[87],"method.":[89],"Our":[90],"results":[91],"show":[92],"use":[95],"induces":[101],"significant":[103],"gain":[104],"extracted":[109],"lexicons.":[110]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}