{"id":"https://openalex.org/W2963937700","doi":"https://doi.org/10.18653/v1/p16-2021","title":"Vocabulary Manipulation for Neural Machine Translation","display_name":"Vocabulary Manipulation for Neural Machine Translation","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2963937700","doi":"https://doi.org/10.18653/v1/p16-2021","mag":"2963937700"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p16-2021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2021","pdf_url":"https://www.aclweb.org/anthology/P16-2021.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short 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/P16-2021.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071533156","display_name":"Haitao Mi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haitao Mi","raw_affiliation_strings":["Watson Research Center IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson Research Center IBM","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430087","display_name":"Zhiguo Wang","orcid":"https://orcid.org/0000-0002-2412-6172"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiguo Wang","raw_affiliation_strings":["Watson Research Center IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson Research Center IBM","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112552652","display_name":"Abe Ittycheriah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abe Ittycheriah","raw_affiliation_strings":["Watson Research Center IBM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Watson Research Center IBM","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":65,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"124","last_page":"129"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.993399977684021,"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":0.8648093938827515},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8221227526664734},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.758452296257019},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7439337968826294},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7346673607826233},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6838744878768921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6797012686729431},{"id":"https://openalex.org/keywords/transfer-based-machine-translation","display_name":"Transfer-based machine translation","score":0.5840538740158081},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5440118312835693},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.5420876145362854},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5355266332626343},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.5139500498771667},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4275771379470825},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40039512515068054},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13976964354515076},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0971614420413971}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8648093938827515},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8221227526664734},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.758452296257019},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7439337968826294},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7346673607826233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6838744878768921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6797012686729431},{"id":"https://openalex.org/C130597682","wikidata":"https://www.wikidata.org/wiki/Q6961922","display_name":"Transfer-based machine translation","level":4,"score":0.5840538740158081},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5440118312835693},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.5420876145362854},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5355266332626343},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.5139500498771667},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4275771379470825},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40039512515068054},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13976964354515076},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0971614420413971},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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:10.18653/v1/p16-2021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2021","pdf_url":"https://www.aclweb.org/anthology/P16-2021.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p16-2021","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-2021","pdf_url":"https://www.aclweb.org/anthology/P16-2021.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 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963937700.pdf","grobid_xml":"https://content.openalex.org/works/W2963937700.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1614298861","https://openalex.org/W2097732278","https://openalex.org/W2100664567","https://openalex.org/W2101105183","https://openalex.org/W2120861206","https://openalex.org/W2124807415","https://openalex.org/W2130942839","https://openalex.org/W2131462252","https://openalex.org/W2133564696","https://openalex.org/W2148708890","https://openalex.org/W2152790380","https://openalex.org/W2157331557","https://openalex.org/W2250803566","https://openalex.org/W2316776689","https://openalex.org/W2595715041","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W2566847733","https://openalex.org/W1559710535","https://openalex.org/W2010336863","https://openalex.org/W2962780935","https://openalex.org/W3204448004","https://openalex.org/W193726211","https://openalex.org/W4378619223","https://openalex.org/W2027317339","https://openalex.org/W2532807140","https://openalex.org/W2384400852"],"abstract_inverted_index":{"In":[0,27],"order":[1],"to":[2,12],"capture":[3],"rich":[4],"language":[5],"phenomena,":[6],"neural":[7,150],"machine":[8,124,151],"translation":[9,88,113,125,140,152],"models":[10],"have":[11],"use":[13],"a":[14,36,44,101,111,116,122],"large":[15,24,148],"vocabulary":[16,105,149],"size,":[17],"which":[18,41],"requires":[19],"high":[20],"computing":[21,75],"time":[22,76],"and":[23,77,99],"memory":[25,79],"usage.":[26,80],"this":[28,32],"paper,":[29],"we":[30,58,71],"alleviate":[31],"issue":[33],"by":[34,142],"introducing":[35],"sentence-level":[37],"or":[38,56,67,93,115],"batch-level":[39,68],"vocabulary,":[40],"is":[42],"only":[43,59],"very":[45,102],"small":[46,103],"sub-set":[47],"of":[48,90,154],"the":[49,61,74,78,87,96,130,147],"full":[50],"output":[51],"vocabulary.":[52,69],"For":[53],"each":[54,91,107],"sentence":[55,108],"batch,":[57],"predict":[60],"target":[62,104],"words":[63],"in":[64,95],"its":[65],"sentencelevel":[66],"Thus,":[70],"reduce":[72],"both":[73],"Our":[81],"method":[82,137],"simply":[83],"takes":[84],"into":[85],"account":[86],"options":[89],"word":[92],"phrase":[94,118],"source":[97],"sentence,":[98],"picks":[100],"for":[106],"based":[109],"on":[110,129],"wordto-word":[112],"model":[114],"bilingual":[117],"library":[119],"learned":[120],"from":[121],"traditional":[123],"model.":[126],"Experimental":[127],"results":[128],"large-scale":[131],"English-to-French":[132],"task":[133],"show":[134],"that":[135],"our":[136],"achieves":[138],"better":[139],"performance":[141],"1":[143],"BLEU":[144],"point":[145],"over":[146],"system":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}