{"id":"https://openalex.org/W2138242477","doi":"https://doi.org/10.1109/slt.2008.4777890","title":"Efficient data selection for machine translation","display_name":"Efficient data selection for machine translation","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2138242477","doi":"https://doi.org/10.1109/slt.2008.4777890","mag":"2138242477"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2008.4777890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2008.4777890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Spoken Language Technology Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103079610","display_name":"Arindam Mandal","orcid":"https://orcid.org/0000-0001-5944-2733"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Mandal","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060715364","display_name":"Dimitra Vergyri","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Vergyri","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076656111","display_name":"W. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Wang","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101494873","display_name":"Jing Zheng","orcid":"https://orcid.org/0000-0003-2724-8471"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Zheng","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Stolcke","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037135105","display_name":"Gokan Tur","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Tur","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015334291","display_name":"Dilek Hakkani-T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Hakkani-Tur","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062598662","display_name":"Necip Faz\u0131l Ayan","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. F. Ayan","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9388,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.9185536,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"264"},"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":0.9988999962806702,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9884999990463257,"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/computer-science","display_name":"Computer science","score":0.8456417322158813},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.811944842338562},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8113678097724915},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6534504890441895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6365945339202881},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6004398465156555},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5407524108886719},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5354597568511963},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5106423497200012},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.454206645488739},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4118732511997223},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3450261950492859},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.16039210557937622},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07066395878791809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456417322158813},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.811944842338562},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8113678097724915},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6534504890441895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6365945339202881},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6004398465156555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5407524108886719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5354597568511963},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5106423497200012},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.454206645488739},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4118732511997223},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3450261950492859},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.16039210557937622},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07066395878791809},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":1,"locations":[{"id":"doi:10.1109/slt.2008.4777890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2008.4777890","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE Spoken Language Technology Workshop","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W32571194","https://openalex.org/W1586104099","https://openalex.org/W1631260214","https://openalex.org/W1707559977","https://openalex.org/W1989658336","https://openalex.org/W2010588484","https://openalex.org/W2035301451","https://openalex.org/W2047295649","https://openalex.org/W2080021732","https://openalex.org/W2097333193","https://openalex.org/W2107695330","https://openalex.org/W2111798208","https://openalex.org/W2136477195","https://openalex.org/W2146574666","https://openalex.org/W2149327368","https://openalex.org/W2161391345","https://openalex.org/W2161482971","https://openalex.org/W2215355985","https://openalex.org/W2356613612","https://openalex.org/W2394860946","https://openalex.org/W2437005631","https://openalex.org/W3149836819","https://openalex.org/W4234016251","https://openalex.org/W6635214705","https://openalex.org/W6636811518","https://openalex.org/W6637606062","https://openalex.org/W6680264786","https://openalex.org/W6681703963","https://openalex.org/W6712079609"],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W209733029","https://openalex.org/W2891480213","https://openalex.org/W3118953353","https://openalex.org/W2158542502","https://openalex.org/W1997978958"],"abstract_inverted_index":{"Performance":[0],"of":[1,11,26,45,82,116,131],"statistical":[2],"machine":[3],"translation":[4,21,126],"(SMT)":[5],"systems":[6],"relies":[7],"on":[8,98],"the":[9,24,71,89,117],"availability":[10],"a":[12,30,80,92],"large":[13],"parallel":[14],"corpus":[15,28],"which":[16],"is":[17,29],"used":[18],"to":[19,48,62,70,129],"estimate":[20],"probabilities.":[22],"However,":[23],"generation":[25],"such":[27],"long":[31],"and":[32,60,104,121],"expensive":[33],"process.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,111],"introduce":[39],"two":[40],"methods":[41,54],"for":[42],"efficient":[43],"selection":[44],"training":[46,119],"data":[47,65,74,100,120],"be":[49],"translated":[50],"by":[51,57],"humans.":[52],"Our":[53,107],"are":[55],"motivated":[56],"active":[58],"learning":[59],"aim":[61],"choose":[63],"new":[64],"that":[66,110,130],"adds":[67],"maximal":[68],"information":[69],"currently":[72],"available":[73,134],"pool.":[75],"The":[76],"first":[77],"method":[78],"uses":[79,91],"measure":[81],"disagreement":[83],"between":[84],"multiple":[85,102],"SMT":[86],"systems,":[87],"whereas":[88],"second":[90],"perplexity":[93],"criterion.":[94],"We":[95],"performed":[96],"experiments":[97],"Chinese-English":[99],"in":[101],"domains":[103],"test":[105],"sets.":[106],"results":[108],"show":[109],"can":[112],"select":[113],"only":[114],"one-fifth":[115],"additional":[118],"achieve":[122],"similar":[123],"or":[124],"better":[125],"performance,":[127],"compared":[128],"using":[132],"all":[133],"data.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}