{"id":"https://openalex.org/W201537780","doi":null,"title":"Domain adaptation of translation models for multilingual applications","display_name":"Domain adaptation of translation models for multilingual applications","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W201537780","mag":"201537780"},"language":"en","primary_location":{"id":"mag:201537780","doi":null,"is_oa":false,"landing_page_url":"https://apps.dtic.mil/dtic/tr/fulltext/u2/a507147.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5106542734","display_name":"Yiming Yang","orcid":"https://orcid.org/0009-0006-5844-7085","observed_orcids":["https://orcid.org/0009-0006-5844-7085","https://orcid.org/0009-0001-2569-2539"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Yang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109861718","display_name":"Jaime Carbonell","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaime Carbonell","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032040828","display_name":"Monica Rogati","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Monica Rogati","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.3215,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82395962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9955999851226807,"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":0.9955999851226807,"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/T10759","display_name":"Translation Studies and Practices","score":0.00139999995008111,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.0010999999940395355,"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/domain-adaptation","display_name":"domain adaptation","score":0.9599999785423279},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.9309999942779541},{"id":"https://openalex.org/keywords/cross-lingual-information-retrieval","display_name":"cross-lingual information retrieval","score":0.9980000257492065},{"id":"https://openalex.org/keywords/query-translation","display_name":"query translation","score":0.8740000128746033},{"id":"https://openalex.org/keywords/training-sample-selection","display_name":"training data selection","score":0.6949999928474426},{"id":"https://openalex.org/keywords/sentence-ranking","display_name":"sentence ranking","score":0.5329999923706055},{"id":"https://openalex.org/keywords/multilingual-applications","display_name":"multilingual applications","score":0.38499999046325684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8585101366043091},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6220417022705078},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6044374704360962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5703843832015991},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5033325552940369},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5011093616485596},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.49061504006385803},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48302730917930603},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.48137548565864563},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4226281940937042},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3727499842643738},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36517763137817383},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.10882732272148132},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08946505188941956},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating 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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:201537780","doi":null,"is_oa":false,"landing_page_url":"https://apps.dtic.mil/dtic/tr/fulltext/u2/a507147.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W29933666","https://openalex.org/W90362830","https://openalex.org/W280151210","https://openalex.org/W1496351660","https://openalex.org/W1498238796","https://openalex.org/W1540719499","https://openalex.org/W1578502111","https://openalex.org/W1590952807","https://openalex.org/W1660390307","https://openalex.org/W1818857488","https://openalex.org/W1941999406","https://openalex.org/W1973923101","https://openalex.org/W1988155782","https://openalex.org/W1990734153","https://openalex.org/W2001343910","https://openalex.org/W2006969979","https://openalex.org/W2014703436","https://openalex.org/W2020743660","https://openalex.org/W2024181699","https://openalex.org/W2047295649","https://openalex.org/W2084849788","https://openalex.org/W2088791674","https://openalex.org/W2101105183","https://openalex.org/W2107990107","https://openalex.org/W2111084382","https://openalex.org/W2111362445","https://openalex.org/W2120084270","https://openalex.org/W2120354757","https://openalex.org/W2120708938","https://openalex.org/W2126815469","https://openalex.org/W2131953535","https://openalex.org/W2137924748","https://openalex.org/W2138970210","https://openalex.org/W2146574666","https://openalex.org/W2158108973","https://openalex.org/W2163302275","https://openalex.org/W2394860946","https://openalex.org/W2435251607","https://openalex.org/W2569308312","https://openalex.org/W2610216665"],"related_works":["https://openalex.org/W2787476709","https://openalex.org/W2754727417","https://openalex.org/W2261339088","https://openalex.org/W2133622676","https://openalex.org/W2009847538","https://openalex.org/W7100631511","https://openalex.org/W2335938761","https://openalex.org/W3209230506","https://openalex.org/W6911515889","https://openalex.org/W2978664055"],"abstract_inverted_index":{"The":[0,222,273],"performance":[1,365],"of":[2,10,32,41,63,101,160,167,264,276,378,388,461],"a":[3,88,99,116,151,158,214,218,283,292,405,430,451],"statistical":[4,438],"translation":[5,21,96,180,203,230,327,337],"algorithm":[6,419],"in":[7,78,105,123,209,240,333,426,435,454],"the":[8,25,33,46,60,168,241,245,257,262,270,373,386,447,462,468,482,486,497],"context":[9],"multilingual":[11,315],"applications":[12],"such":[13,71,309],"as":[14,72,409,411,485,501,503],"cross-lingual":[15,317],"information":[16,318],"retrieval":[17,319],"(CLIR)":[18],"and":[19,28,39,75,92,110,200,234,254,320,343,370,437,472,478],"machine":[20,321],"(MT)":[22],"depends":[23],"on":[24,115,128,139,157,298,446],"quality,":[26],"quantity":[27,62],"proper":[29],"domain":[30,118,220,228,379],"matching":[31],"training":[34,42,185,443,455],"data.":[35,302,382],"Traditionally,":[36],"manual":[37,83,140],"selection":[38,470],"customization":[40,84],"resources":[43,65],"has":[44],"been":[45],"prevailing":[47],"approach.":[48],"In":[49,323],"addition":[50],"to":[51,59,90,173,187,206,211,269,291,312,339,358,363,371,392,428],"being":[52],"labor-intensive,":[53],"this":[54,175,304],"approach":[55],"does":[56,85],"not":[57,86,120,132,163],"scale":[58],"large":[61,376],"heterogeneous":[64,102,340],"that":[66,285,441],"have":[67],"recently":[68],"become":[69],"available,":[70],"parallel":[73,184,381,394],"text":[74],"bilingual":[76],"thesauri":[77],"various":[79,106],"domains.":[80],"More":[81],"importantly,":[82],"offer":[87],"solution":[89],"efficiently":[91],"effectively":[93],"producing":[94],"tailored":[95],"models":[97,113,126,137,155,181,328,338],"for":[98,134,145,165,329,375,475],"mixture":[100,159],"target":[103,189,215,341,349],"documents":[104,130],"domains,":[107],"topics,":[108],"languages":[109],"genres.":[111],"Translation":[112],"trained":[114,127,138,156,297],"general":[117],"do":[119],"work":[121],"well":[122,410,502],"technical":[124],"domains;":[125],"written":[129],"are":[131,162,252],"appropriate":[133],"spoken":[135],"dialogue;":[136],"transcripts":[141,148],"can":[142,286],"be":[143],"sub-optimal":[144],"translating":[146],"noisy":[147],"produced":[149],"by":[150,177,282],"speech":[152],"recognizer;":[153],"finally,":[154],"topics":[161],"optimal":[164],"any":[166],"topic-specific":[169],"documents.":[170],"\r\nWe":[171],"seek":[172],"address":[174,385],"challenge":[176,387],"automatically":[178,198],"adapting":[179],"(and":[182],"implicitly":[183],"resources)":[186],"specific":[188,219,300,380],"domains":[190],"or":[191,217],"sub-domains.":[192],"\r\nThe":[193],"high-level":[194],"adaptation":[195,242,310,356],"process":[196,243],"involves":[197],"weighting":[199,290],"combining":[201,389],"multiple":[202,390],"resources,":[204],"according":[205],"several":[207],"criteria,":[208],"order":[210,427],"better":[212],"match":[213],"corpus":[216],"sample.":[221],"criteria":[223,251,391,493],"we":[224,306,325,335],"examine":[225,307],"include":[226],"lexical-level":[227],"match,":[229],"quality":[231],"estimates,":[232],"size,":[233],"taxonomy":[235],"representation.":[236],"An":[237],"orthogonal":[238],"dimension":[239],"is":[244,279],"granularity":[246],"level":[247,259],"at":[248],"which":[249,420],"these":[250],"measured":[253],"applied:":[255],"from":[256,288],"collection":[258],"-":[260,268],"under":[261,366],"assumption":[263],"homogeneous":[265],"within-collection":[266],"data":[267,444,456],"document":[271],"level.":[272],"relative":[274],"contribution":[275],"each":[277],"criterion":[278],"subsequently":[280],"determined":[281],"model":[284,296,351],"range":[287],"uniform":[289,498],"global":[293,406],"non-linear":[294],"optimization":[295,407],"application":[299],"evaluation":[301],"\r\nIn":[303],"thesis,":[305],"how":[308],"applies":[311],"two":[313],"important":[314],"applications:":[316],"translation.":[322],"CLIR,":[324],"adapt":[326,336],"domain-specific":[330],"query":[331],"translation;":[332],"MT,":[334],"corpora":[342],"compare":[344],"them":[345],"with":[346],"previously":[347],"studied":[348],"language":[350],"adaptation.":[352,506],"We":[353,383,397],"use":[354],"our":[355],"algorithms":[357],"enhance":[359],"state-of-the-art":[360],"systems,":[361],"seeking":[362],"improve":[364],"different":[367],"testing":[368],"conditions":[369],"reduce":[372],"demand":[374],"amounts":[377],"also":[384],"rank":[393],"sentence":[395],"candidates.":[396],"investigate":[398],"Continuous":[399],"Reactive":[400,412],"Tabu":[401],"Search":[402],"(CRTS)":[403],"[2],":[404],"method,":[408],"Affine":[413],"Shaker":[414],"(RASH)":[415],"[6],":[416],"an":[417],"efficient":[418],"continuously":[421],"adjusts":[422],"its":[423],"search":[424],"area":[425],"identify":[429],"local":[431],"minimum.":[432],"\r\nOur":[433],"experiments":[434],"CLIR":[436,477],"MT":[439],"indicate":[440],"selecting":[442],"based":[445],"above-mentioned":[448],"approaches":[449],"allows":[450],"significant":[452],"reduction":[453],"while":[457],"preserving":[458],"about":[459],"90%":[460],"performance.":[463],"This":[464],"result":[465],"significantly":[466],"surpasses":[467],"random":[469],"approach,":[471],"it":[473],"holds":[474],"both":[476],"MT.":[479],"As":[480],"expected,":[481],"difference":[483],"increases":[484],"subdomain":[487],"becomes":[488],"more":[489],"specific.":[490],"Our":[491],"optimized":[492],"weights":[494],"considerably":[495],"outperform":[496],"distribution":[499],"baseline,":[500],"lexical":[504],"similarity":[505]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-09-24T07:57:37.273135","created_date":"2016-06-24T00:00:00"}