{"id":"https://openalex.org/W2133837072","doi":"https://doi.org/10.3115/1218955.1219022","title":"A geometric view on bilingual lexicon extraction from comparable corpora","display_name":"A geometric view on bilingual lexicon extraction from comparable corpora","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2133837072","doi":"https://doi.org/10.3115/1218955.1219022","mag":"2133837072"},"language":"en","primary_location":{"id":"doi:10.3115/1218955.1219022","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1219022","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1219022","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics  - ACL '04","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1219022","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014352159","display_name":"\u00c9ric Gaussier","orcid":"https://orcid.org/0000-0002-8858-3233"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"E. Gaussier","raw_affiliation_strings":["Xerox Research Centre Europe, Meylan, France","Xerox Research Centre Europe, Meylan, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France#TAB#","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082168699","display_name":"J.-M. Renders","orcid":null},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J.-M. Renders","raw_affiliation_strings":["Xerox Research Centre Europe, Meylan, France","Xerox Research Centre Europe, Meylan, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France#TAB#","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101413273","display_name":"Irina Matveeva","orcid":"https://orcid.org/0009-0001-1501-3109"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I. Matveeva","raw_affiliation_strings":["University of Chicago, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065257553","display_name":"Cyril Goutte","orcid":"https://orcid.org/0000-0003-4939-6555"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Goutte","raw_affiliation_strings":["Xerox Research Centre Europe, Meylan, France","Xerox Research Centre Europe, Meylan, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France#TAB#","institution_ids":["https://openalex.org/I33976269"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085566571","display_name":"Herv\u00e9 D\u00e9jean","orcid":"https://orcid.org/0000-0002-9837-5358"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"H. D\u00e9jean","raw_affiliation_strings":["Xerox Research Centre Europe, Meylan, France","Xerox Research Centre Europe, Meylan, France#TAB#"],"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France","institution_ids":["https://openalex.org/I33976269"]},{"raw_affiliation_string":"Xerox Research Centre Europe, Meylan, France#TAB#","institution_ids":["https://openalex.org/I33976269"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014352159"],"corresponding_institution_ids":["https://openalex.org/I33976269"],"apc_list":null,"apc_paid":null,"fwci":6.0077,"has_fulltext":true,"cited_by_count":128,"citation_normalized_percentile":{"value":0.9609412,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"526","last_page":"es"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9902999997138977,"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/lexicon","display_name":"Lexicon","score":0.8983806371688843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7988105416297913},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6675660014152527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6505271196365356},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.44859376549720764},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.43597424030303955}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.8983806371688843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7988105416297913},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6675660014152527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6505271196365356},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.44859376549720764},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.43597424030303955},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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":4,"locations":[{"id":"doi:10.3115/1218955.1219022","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1219022","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1219022","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics  - ACL '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.113.1046","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.113.1046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/acl2004/main/pdf/157_pdf_2-col.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.7026","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.7026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.xrce.xerox.com/Publications/Attachments/2004-013/2004_013.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.98.6878","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.98.6878","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mt-archive.info/ACL-2004-Gaussier.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1218955.1219022","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1219022","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1219022","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics  - ACL '04","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320718","display_name":"Department of Scientific and Industrial Research, Ministry of Science and Technology, India","ror":"https://ror.org/049nrz535"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2133837072.pdf","grobid_xml":"https://content.openalex.org/works/W2133837072.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W71111251","https://openalex.org/W1549114989","https://openalex.org/W1588424744","https://openalex.org/W1612003148","https://openalex.org/W1889220380","https://openalex.org/W1972871876","https://openalex.org/W2048610319","https://openalex.org/W2049633694","https://openalex.org/W2079317503","https://openalex.org/W2084988910","https://openalex.org/W2107042471","https://openalex.org/W2121415745","https://openalex.org/W2125972593","https://openalex.org/W2134731454","https://openalex.org/W2139812240","https://openalex.org/W2147152072","https://openalex.org/W2163953154","https://openalex.org/W2166023018","https://openalex.org/W2166473218","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2140536630","https://openalex.org/W3195005284","https://openalex.org/W2391730868","https://openalex.org/W4394659737","https://openalex.org/W2759814045","https://openalex.org/W2118055728","https://openalex.org/W4399756845","https://openalex.org/W1831473261","https://openalex.org/W4293870971","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,49],"geometric":[3],"view":[4],"on":[5],"bilingual":[6],"lexicon":[7],"extraction":[8],"from":[9],"comparable":[10],"corpora,":[11],"which":[12],"allows":[13],"to":[14],"re-interpret":[15],"the":[16,39,53],"methods":[17,29],"proposed":[18],"so":[19],"far":[20],"and":[21,41],"identify":[22],"unresolved":[23],"problems.":[24,35],"This":[25],"motivates":[26],"three":[27],"new":[28],"that":[30],"aim":[31],"at":[32],"solving":[33],"these":[34,44],"Empirical":[36],"evaluation":[37],"shows":[38],"strengths":[40],"weaknesses":[42],"of":[43,55],"methods,":[45],"as":[46,48],"well":[47],"significant":[50],"gain":[51],"in":[52],"accuracy":[54],"extracted":[56],"lexicons.":[57]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}