{"id":"https://openalex.org/W2740514420","doi":"https://doi.org/10.18653/v1/e17-2103","title":"Unsupervised Training for Large Vocabulary Translation Using Sparse Lexicon and Word Classes","display_name":"Unsupervised Training for Large Vocabulary Translation Using Sparse Lexicon and Word Classes","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2740514420","doi":"https://doi.org/10.18653/v1/e17-2103","mag":"2740514420"},"language":"en","primary_location":{"id":"doi:10.18653/v1/e17-2103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-2103","pdf_url":"https://www.aclweb.org/anthology/E17-2103.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 15th Conference of the European Chapter of the\n          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://www.aclweb.org/anthology/E17-2103.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005673540","display_name":"Yunsu Kim","orcid":"https://orcid.org/0000-0002-1375-005X"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yunsu Kim","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062752026","display_name":"Julian Schamper","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julian Schamper","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group RWTH Aachen University"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005673540"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.4157,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72016141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"650","last_page":"656"},"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":0.9998000264167786,"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":0.9927999973297119,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8385673761367798},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7898530960083008},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7125591039657593},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6871894001960754},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6238948106765747},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5420651435852051},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.535049557685852},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5065358877182007},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45991742610931396},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45731234550476074},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11868947744369507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385673761367798},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7898530960083008},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7125591039657593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6871894001960754},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6238948106765747},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5420651435852051},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.535049557685852},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5065358877182007},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45991742610931396},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45731234550476074},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11868947744369507},{"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/e17-2103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-2103","pdf_url":"https://www.aclweb.org/anthology/E17-2103.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 15th Conference of the European Chapter of the\n          Association for Computational Linguistics: Volume 2, Short Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:686521","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-213002%22","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"7 Seiten (2017).","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/e17-2103","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/e17-2103","pdf_url":"https://www.aclweb.org/anthology/E17-2103.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 15th Conference of the European Chapter of the\n          Association for Computational Linguistics: Volume 2, Short Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8884546066","display_name":"QT21: Quality Translation 21","funder_award_id":"645452","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320319634","display_name":"Nuance Foundation","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740514420.pdf","grobid_xml":"https://content.openalex.org/works/W2740514420.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W1199002571","https://openalex.org/W1570013475","https://openalex.org/W1934041838","https://openalex.org/W2049633694","https://openalex.org/W2080018251","https://openalex.org/W2099873701","https://openalex.org/W2102028293","https://openalex.org/W2103042430","https://openalex.org/W2110168585","https://openalex.org/W2113788796","https://openalex.org/W2117827367","https://openalex.org/W2121227244","https://openalex.org/W2121745180","https://openalex.org/W2135391077","https://openalex.org/W2136346830","https://openalex.org/W2156985047","https://openalex.org/W2161792612","https://openalex.org/W2164746297","https://openalex.org/W2169360026","https://openalex.org/W2172267041","https://openalex.org/W2184135559","https://openalex.org/W2250600644","https://openalex.org/W2250640401","https://openalex.org/W2514378259","https://openalex.org/W3001379634"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W1997182898"],"abstract_inverted_index":{"We":[0,19],"address":[1],"for":[2,8,54],"the":[3,22,42,47,55,60,69],"first":[4],"time":[5],"unsupervised":[6,79],"training":[7,62],"a":[9,28,50],"translation":[10,30,80],"task":[11],"with":[12,49,63],"hundreds":[13],"of":[14,16],"thousands":[15],"vocabulary":[17],"words.":[18],"scale":[20],"up":[21],"expectation-maximization":[23],"(EM)":[24],"algorithm":[25],"to":[26],"learn":[27],"large":[29],"table":[31],"without":[32],"any":[33],"parallel":[34],"text":[35],"or":[36],"seed":[37],"lexicon.":[38,56],"First,":[39],"we":[40,58],"solve":[41],"memory":[43],"bottleneck":[44],"and":[45],"enforce":[46],"sparsity":[48],"simple":[51],"thresholding":[52],"scheme":[53],"Second,":[57],"initialize":[59],"lexicon":[61],"word":[64],"classes,":[65],"which":[66],"efficiently":[67],"boosts":[68],"performance.":[70],"Our":[71],"methods":[72],"produced":[73],"promising":[74],"results":[75],"on":[76],"two":[77],"large-scale":[78],"tasks.":[81]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-19T08:26:33.389920","created_date":"2025-10-10T00:00:00"}