{"id":"https://openalex.org/W2514378259","doi":"https://doi.org/10.18653/v1/w16-2212","title":"A Comparative Study on Vocabulary Reduction for Phrase Table Smoothing","display_name":"A Comparative Study on Vocabulary Reduction for Phrase Table Smoothing","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2514378259","doi":"https://doi.org/10.18653/v1/w16-2212","mag":"2514378259"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w16-2212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2212","pdf_url":"https://www.aclweb.org/anthology/W16-2212.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 First Conference on Machine Translation: Volume 1, Research Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W16-2212.pdf","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Yunsu Kim","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069414172","display_name":"Andreas Guta","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":"Andreas Guta","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067263769","display_name":"Joern Wuebker","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":"Joern Wuebker","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany","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, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Group RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"110","last_page":"117"},"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":0.9998999834060669,"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":0.9955000281333923,"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/phrase","display_name":"Phrase","score":0.9085578918457031},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.8081951141357422},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7929525375366211},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7312179207801819},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.590064525604248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5488614439964294},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5043627023696899},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.466513067483902},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4101749658584595},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.387263685464859},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20545604825019836},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14854106307029724}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.9085578918457031},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.8081951141357422},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7929525375366211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312179207801819},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.590064525604248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5488614439964294},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5043627023696899},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.466513067483902},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4101749658584595},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.387263685464859},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20545604825019836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14854106307029724},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w16-2212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2212","pdf_url":"https://www.aclweb.org/anthology/W16-2212.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 First Conference on Machine Translation: Volume 1, Research Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:668731","is_oa":true,"landing_page_url":"https://publications.rwth-aachen.de/record/668731","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 54th Annual Meeting of the Association for Computational Linguistics - proceedings of the First Conference on Machine Translation (WMT) : August 7-12, 2016, Berlin, Germany : ACL 2016. - Volume 1, Research Papers<br/>1. Conference on Machine Translation, WMT16, Berlin, Germany, 2016-08-11 - 2016-08-12","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/w16-2212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w16-2212","pdf_url":"https://www.aclweb.org/anthology/W16-2212.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 First Conference on Machine Translation: Volume 1, Research Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[{"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/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/W2514378259.pdf","grobid_xml":"https://content.openalex.org/works/W2514378259.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W130850236","https://openalex.org/W222053410","https://openalex.org/W1199002571","https://openalex.org/W1916559533","https://openalex.org/W2083460949","https://openalex.org/W2095755718","https://openalex.org/W2110168585","https://openalex.org/W2111798208","https://openalex.org/W2113788796","https://openalex.org/W2121227244","https://openalex.org/W2127318480","https://openalex.org/W2128634885","https://openalex.org/W2146574666","https://openalex.org/W2153653739","https://openalex.org/W2163255203","https://openalex.org/W2250907725","https://openalex.org/W2251369387","https://openalex.org/W2296354688","https://openalex.org/W2528305545","https://openalex.org/W3211848854","https://openalex.org/W4241645538"],"related_works":["https://openalex.org/W2383807498","https://openalex.org/W2039546652","https://openalex.org/W1978572805","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W2149980199","https://openalex.org/W2019977573","https://openalex.org/W1997182898"],"abstract_inverted_index":{"This":[0,36],"work":[1],"systematically":[2],"analyzes":[3],"the":[4,23,32,42],"smoothing":[5,26,61],"effect":[6],"of":[7,25,34],"vocabulary":[8,55],"reduction":[9,56],"for":[10,60],"phrase":[11,44,63],"translation":[12,45],"models.":[13],"We":[14],"extensively":[15],"compare":[16],"various":[17],"word-level":[18],"vocabularies":[19],"to":[20],"show":[21],"that":[22,41,54],"performance":[24],"is":[27,47,57],"not":[28],"significantly":[29],"affected":[30],"by":[31],"choice":[33],"vocabulary.":[35],"result":[37],"provides":[38],"empirical":[39],"evidence":[40],"standard":[43],"model":[46],"extremely":[48],"sparse.":[49],"Our":[50],"experiments":[51],"also":[52],"reveal":[53],"more":[58],"effective":[59],"large-scale":[62],"tables.":[64]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}