{"id":"https://openalex.org/W2250863245","doi":"https://doi.org/10.3115/v1/e14-4022","title":"Using a Random Forest Classifier to Compile Bilingual Dictionaries of Technical Terms from Comparable Corpora","display_name":"Using a Random Forest Classifier to Compile Bilingual Dictionaries of Technical Terms from Comparable Corpora","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2250863245","doi":"https://doi.org/10.3115/v1/e14-4022","mag":"2250863245"},"language":"en","primary_location":{"id":"doi:10.3115/v1/e14-4022","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-4022","pdf_url":"https://aclanthology.org/E14-4022.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/E14-4022.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077625160","display_name":"Georgios Kontonatsios","orcid":"https://orcid.org/0000-0001-5935-4709"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","GB"],"is_corresponding":true,"raw_author_name":"Georgios Kontonatsios","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","School of Computer Science, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060320466","display_name":"Ioannis Korkontzelos","orcid":"https://orcid.org/0000-0001-8052-2471"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Ioannis Korkontzelos","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","School of Computer Science, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112241147","display_name":"Jun\u2019ichi Tsujii","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun'ichi Tsujii","raw_affiliation_strings":["National Centre for Text Mining, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"National Centre for Text Mining, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077976343","display_name":"Sophia Ananiadou","orcid":"https://orcid.org/0000-0002-4097-9191"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Sophia Ananiadou","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","School of Computer Science, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077625160"],"corresponding_institution_ids":["https://openalex.org/I28407311","https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":4.2285,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94635316,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"116"},"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":0.9979000091552734,"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/T12353","display_name":"Lexicography and Language Studies","score":0.9930999875068665,"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":0.7113958597183228},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.654394268989563},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5944406986236572},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5757594704627991},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5204775333404541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.516435444355011},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3472376763820648},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14922210574150085},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.0820624828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113958597183228},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.654394268989563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5944406986236572},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5757594704627991},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5204775333404541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.516435444355011},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3472376763820648},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14922210574150085},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0820624828338623}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3115/v1/e14-4022","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-4022","pdf_url":"https://aclanthology.org/E14-4022.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/cee26dd0-0971-4cbc-a6e9-26b388c71a8a","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/cee26dd0-0971-4cbc-a6e9-26b388c71a8a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kontonatsios, G, Korkontzelos, I, Tsujii, J & Ananiadou, S 2014, Using a Random Forest Classifier to Compile Bilingual Dictionaries of Technical Terms from Comparable Corpora. in Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers. Association for Computational Linguistics, pp. 111-116. < http://www.aclweb.org/anthology/E14-4022 >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.670.7896","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.670.7896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/E/E14/E14-4022.pdf","raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:publications/b65defa5-1052-48f3-a852-9ebc93b7d075","is_oa":true,"landing_page_url":"https://research.edgehill.ac.uk/en/publications/b65defa5-1052-48f3-a852-9ebc93b7d075","pdf_url":null,"source":{"id":"https://openalex.org/S4306402462","display_name":"Edge Hill University Research Information Repository (Edge Hill University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165525304","host_organization_name":"Edge Hill University","host_organization_lineage":["https://openalex.org/I165525304"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kontonatsios, G, Korkontzelos, Y, Tsujii, J & Ananiadou, S 2014, 'Using a Random Forest Classifier to Compile Bilingual Dictionaries of Technical Terms from Comparable Corpora', Paper presented at 14th Conference of the European Chapter of the Association for Computational Linguistics, Gothenburg, Sweden, 26/04/14 - 30/04/14 pp. 111-116. < http://www.aclweb.org/anthology/E14-4022 >","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:repository.edgehill.ac.uk:6991","is_oa":false,"landing_page_url":"http://repository.edgehill.ac.uk/6991/1/E14-4022.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922844","display_name":"Edge Hill University Research Archive","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":{"id":"doi:10.3115/v1/e14-4022","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/e14-4022","pdf_url":"https://aclanthology.org/E14-4022.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, volume 2: Short Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250863245.pdf","grobid_xml":"https://content.openalex.org/works/W2250863245.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W31621926","https://openalex.org/W72471529","https://openalex.org/W116705248","https://openalex.org/W1582850894","https://openalex.org/W1693107767","https://openalex.org/W2008248260","https://openalex.org/W2011248508","https://openalex.org/W2041232209","https://openalex.org/W2054890041","https://openalex.org/W2101105183","https://openalex.org/W2102749417","https://openalex.org/W2124807415","https://openalex.org/W2138584836","https://openalex.org/W2140460368","https://openalex.org/W2156170481","https://openalex.org/W2156985047","https://openalex.org/W2158901977","https://openalex.org/W2162967019","https://openalex.org/W2581587939","https://openalex.org/W2595715041","https://openalex.org/W2788439731","https://openalex.org/W2911964244","https://openalex.org/W4253938478","https://openalex.org/W4302780227"],"related_works":["https://openalex.org/W4240253816","https://openalex.org/W3096456556","https://openalex.org/W2169584677","https://openalex.org/W2979513934","https://openalex.org/W4232954277","https://openalex.org/W3193043704","https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W2020341030","https://openalex.org/W2889302474"],"abstract_inverted_index":{"Georgios":[0],"Kontonatsios,":[1],"Ioannis":[2],"Korkontzelos,":[3],"Jun\u2019ichi":[4],"Tsujii,":[5],"Sophia":[6],"Ananiadou.":[7],"Proceedings":[8],"of":[9,13,17],"the":[10,14,18],"14th":[11],"Conference":[12],"European":[15],"Chapter":[16],"Association":[19],"for":[20],"Computational":[21],"Linguistics,":[22],"volume":[23],"2:":[24],"Short":[25],"Papers.":[26],"2014.":[27]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}