{"id":"https://openalex.org/W2060786818","doi":"https://doi.org/10.1109/taslp.2014.2381882","title":"Optimizing Instance Selection for Statistical Machine Translation with Feature Decay Algorithms","display_name":"Optimizing Instance Selection for Statistical Machine Translation with Feature Decay Algorithms","publication_year":2014,"publication_date":"2014-12-19","ids":{"openalex":"https://openalex.org/W2060786818","doi":"https://doi.org/10.1109/taslp.2014.2381882","mag":"2060786818"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2381882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2381882","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5052353826","display_name":"Ergun Bi\u00e7ici","orcid":"https://orcid.org/0000-0002-2293-2031"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ergun Bicici","raw_affiliation_strings":["Ko\u00e7 University, Istanbul, Turkey","The Department of Computer Engineering, Ko\u00e7 University Istanbul, Istanbul, Turkey#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ko\u00e7 University, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]},{"raw_affiliation_string":"The Department of Computer Engineering, Ko\u00e7 University Istanbul, Istanbul, Turkey#TAB#","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013522667","display_name":"Deniz Y\u00fcret","orcid":"https://orcid.org/0000-0002-7039-0046"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Deniz Yuret","raw_affiliation_strings":["Ko\u00e7 University, Istanbul, Turkey","The Department of Computer Engineering, Ko\u00e7 University Istanbul, Istanbul, Turkey#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ko\u00e7 University, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]},{"raw_affiliation_string":"The Department of Computer Engineering, Ko\u00e7 University Istanbul, Istanbul, Turkey#TAB#","institution_ids":["https://openalex.org/I1351752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.0353,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97463566,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"23","issue":"2","first_page":"339","last_page":"350"},"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":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":0.9776999950408936,"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/machine-translation","display_name":"Machine translation","score":0.7654411792755127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7564413547515869},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.7389441728591919},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7052175402641296},{"id":"https://openalex.org/keywords/evaluation-of-machine-translation","display_name":"Evaluation of machine translation","score":0.6793511509895325},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.649068295955658},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6166208982467651},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5415703058242798},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.539532482624054},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5186659097671509},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49315398931503296},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.473283976316452},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.47288742661476135},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.45288538932800293},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.45179250836372375},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41044747829437256},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3880709707736969},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.21584278345108032},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1511515974998474},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.1022610068321228}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7654411792755127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7564413547515869},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.7389441728591919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7052175402641296},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.6793511509895325},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.649068295955658},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6166208982467651},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5415703058242798},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.539532482624054},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5186659097671509},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49315398931503296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.473283976316452},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.47288742661476135},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.45288538932800293},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.45179250836372375},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41044747829437256},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3880709707736969},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.21584278345108032},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1511515974998474},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.1022610068321228},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2014.2381882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2381882","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W64777181","https://openalex.org/W99956235","https://openalex.org/W1507039213","https://openalex.org/W1522553155","https://openalex.org/W1586104099","https://openalex.org/W1957053378","https://openalex.org/W1979812056","https://openalex.org/W1999700404","https://openalex.org/W2087735403","https://openalex.org/W2096549294","https://openalex.org/W2101816610","https://openalex.org/W2105410942","https://openalex.org/W2113131493","https://openalex.org/W2118296893","https://openalex.org/W2119396705","https://openalex.org/W2123318312","https://openalex.org/W2124807415","https://openalex.org/W2126400076","https://openalex.org/W2126747756","https://openalex.org/W2132001515","https://openalex.org/W2135573497","https://openalex.org/W2136477195","https://openalex.org/W2137698233","https://openalex.org/W2137894131","https://openalex.org/W2138242477","https://openalex.org/W2141799614","https://openalex.org/W2157963512","https://openalex.org/W2178456880","https://openalex.org/W2250612599","https://openalex.org/W2251749997","https://openalex.org/W2251869843","https://openalex.org/W2257408573","https://openalex.org/W2270190199","https://openalex.org/W2604377206","https://openalex.org/W2783135427","https://openalex.org/W2891920428","https://openalex.org/W3104143564","https://openalex.org/W3145128584","https://openalex.org/W4246219036","https://openalex.org/W6602722986","https://openalex.org/W6631428405","https://openalex.org/W6635214705","https://openalex.org/W6680167199","https://openalex.org/W6680325970","https://openalex.org/W6691646088"],"related_works":["https://openalex.org/W3151736118","https://openalex.org/W3097971125","https://openalex.org/W2395641992","https://openalex.org/W2962780935","https://openalex.org/W4280571180","https://openalex.org/W2099607809","https://openalex.org/W3021126373","https://openalex.org/W92588874","https://openalex.org/W2807475932","https://openalex.org/W2903057408"],"abstract_inverted_index":{"We":[0,68],"introduce":[1],"FDA5":[2,43,74,136,197,215,269,317],"for":[3,54,85,226,343],"efficient":[4],"parameterization,":[5],"optimization,":[6],"and":[7,56,60,81,175,228,249,263,306,347],"implementation":[8],"of":[9,16,28,95,121,130,150,165,173,192,205,238,247,283,298,340,349,361],"feature":[10,22,58],"decay":[11],"algorithms":[12,19],"(FDA),":[13],"a":[14,90,128,146,265,279,326,356],"class":[15],"instance":[17,304],"selection":[18,94],"that":[20,38,72,127],"use":[21],"decay.":[23],"FDA":[24,229],"increase":[25],"the":[26,29,100,105,115,122,131,151,166,183,193,206,217,222,239,284,289,299,309,322,341,344,350,362,375],"diversity":[27],"selected":[30,134,148,281],"training":[31,96,132,168,185,195,208,241,256,363],"set":[32,102,133,186],"by":[33,135,188,220,313],"devaluing":[34],"features":[35],"(i.e.,":[36],"n-grams)":[37],"have":[39],"already":[40],"been":[41],"included.":[42],"decides":[44],"which":[45],"instances":[46,97],"to":[47,75,79,99,140,145,157,162,182,232,244,254,273,278,302,320,324,331],"select":[48],"based":[49],"on":[50,114],"three":[51],"functions":[52,78],"used":[53],"initializing":[55],"decaying":[57],"values":[59],"scaling":[61],"sentence":[62,118],"scores":[63],"controlled":[64],"with":[65,334,355,374],"five":[66],"parameters.":[67],"present":[69],"optimization":[70],"techniques":[71],"allow":[73],"adapt":[76],"these":[77],"in-domain":[80],"out-of-domain":[82,379],"translation":[83,107,111,227,259,329],"tasks":[84,260],"different":[86],"language":[87],"pairs.":[88],"In":[89,109,210,258],"transductive":[91],"learning":[92,213],"setting,":[93,214],"relevant":[98],"test":[101],"can":[103,137,154,176,270,287,307],"improve":[104],"final":[106],"quality.":[108],"machine":[110,328],"experiments":[112],"performed":[113],"2":[116],"million":[117],"English-German":[119],"section":[120],"Europarl":[123],"corpus,":[124],"we":[125],"show":[126],"subset":[129,149,282],"gain":[138,155,271],"up":[139,156,231,272],"3.22":[141],"BLEU":[142,159,180,234,251,275,291,315,371],"points":[143,160,181,235,252,276,372],"compared":[144,161,243,253,277,301,354],"randomly":[147,280],"same":[152,285,290],"size,":[153,286],"0.41":[158],"using":[163,170,189,236,245,293,337,359],"all":[164,246,360],"available":[167,240,365],"data":[169,242,300,364],"only":[171,190,338,369],"15%":[172,204],"it,":[174],"reach":[177],"within":[178],"0.5":[179],"full":[184,194,207,310],"result":[187,312],"2.7%":[191],"data.":[196],"peaks":[198],"at":[199],"around":[200],"8M":[201],"words":[202,336],"or":[203],"set.":[209,257],"an":[211],"active":[212],"minimizes":[216],"human":[218],"effort":[219],"identifying":[221],"most":[223],"informative":[224],"sentences":[225],"gains":[230],"0.45":[233],"3/5":[237],"it":[248],"1.12":[250],"random":[255,303],"involving":[261],"English":[262],"Turkish,":[264],"morphologically":[266],"rich":[267],"language,":[268],"11.52":[274],"achieve":[288],"score":[292],"as":[294,296],"little":[295],"4%":[297],"selection,":[305],"exceed":[308],"dataset":[311],"0.78":[314],"points.":[316],"is":[318],"able":[319],"reduce":[321],"time":[323],"build":[325],"statistical":[327],"system":[330,358,377],"about":[332],"half":[333],"1M":[335],"3%":[339],"space":[342,352],"phrase":[345],"table":[346],"8%":[348],"overall":[351],"when":[353],"baseline":[357,376],"yet":[366],"still":[367],"obtain":[368],"0.58":[370],"difference":[373],"in":[378],"translation.":[380]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}