{"id":"https://openalex.org/W2147262247","doi":null,"title":"Adaptation Data Selection using Neural Language Models: Experiments in Machine Translation","display_name":"Adaptation Data Selection using Neural Language Models: Experiments in Machine Translation","publication_year":2013,"publication_date":"2013-08-01","ids":{"openalex":"https://openalex.org/W2147262247","mag":"2147262247"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.386.4633","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.386.4633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/P/P13/P13-2119.pdf","raw_type":"text"},"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/A5070418792","display_name":"Kevin Duh","orcid":"https://orcid.org/0000-0001-8107-4383","observed_orcids":["https://orcid.org/0000-0001-8107-4383"]},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kevin Duh","raw_affiliation_strings":[", Nara Institute of Science and Technology"],"raw_orcid":"https://orcid.org/0000-0001-8107-4383","affiliations":[{"raw_affiliation_string":", Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789","observed_orcids":["https://orcid.org/0000-0002-2072-3789"]},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":[", Nara Institute of Science and Technology"],"raw_orcid":"https://orcid.org/0000-0002-2072-3789","affiliations":[{"raw_affiliation_string":", Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051961507","display_name":"Katsuhito Sudoh","orcid":"https://orcid.org/0000-0002-2122-9846","observed_orcids":["https://orcid.org/0000-0002-2122-9846"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katsuhito Sudoh","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2122-9846","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023441468","display_name":"Hajime Tsukada","orcid":"https://orcid.org/0000-0002-7917-1843","observed_orcids":["https://orcid.org/0000-0002-7917-1843"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hajime Tsukada","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7917-1843","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.5896,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.98657113,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"2","issue":null,"first_page":"678","last_page":"683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9916999936103821,"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":0.9916999936103821,"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":0.003800000064074993,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.002899999963119626,"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/dataset-selection","display_name":"data selection","score":0.8880000114440918},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.9459999799728394},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.8820000290870667},{"id":"https://openalex.org/keywords/neural-language-models","display_name":"neural language models","score":0.9990000128746033},{"id":"https://openalex.org/keywords/word-embeddings","display_name":"word embeddings","score":0.6399999856948853},{"id":"https://openalex.org/keywords/n-gram-language-models","display_name":"n-gram language models","score":0.7839999794960022},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.45500001311302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8435076475143433},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.771941065788269},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7572301626205444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7144542932510376},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6791537404060364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6628808379173279},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.6496862769126892},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5318904519081116},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5231898427009583},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5057952404022217},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.502556324005127},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45123913884162903},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44967156648635864},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.4447833299636841},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.425631582736969},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42511314153671265},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4141438603401184},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.22556117177009583},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.22128233313560486},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1050393283367157},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.386.4633","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.386.4633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/P/P13/P13-2119.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.703.3965","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.703.3965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cl.naist.jp/%7Ekevinduh/papers/duh13neural.pdf","raw_type":"text"},{"id":"mag:2147262247","doi":null,"is_oa":false,"landing_page_url":"https://cs.jhu.edu/~kevinduh/papers/duh13neural.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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W222053410","https://openalex.org/W1575384945","https://openalex.org/W1848260265","https://openalex.org/W1905522558","https://openalex.org/W1965154800","https://openalex.org/W1970689298","https://openalex.org/W2040711288","https://openalex.org/W2072128103","https://openalex.org/W2101105183","https://openalex.org/W2105402874","https://openalex.org/W2107878390","https://openalex.org/W2117278770","https://openalex.org/W2132339004","https://openalex.org/W2143719855","https://openalex.org/W2149327368","https://openalex.org/W2153508793","https://openalex.org/W2171928131","https://openalex.org/W2184135559","https://openalex.org/W2250379827","https://openalex.org/W2251150025","https://openalex.org/W2251202280","https://openalex.org/W2399188371","https://openalex.org/W2406343028","https://openalex.org/W3167516426"],"related_works":["https://openalex.org/W7098195601","https://openalex.org/W2577063019","https://openalex.org/W3198953535","https://openalex.org/W7100812987","https://openalex.org/W3198270094","https://openalex.org/W2568088849","https://openalex.org/W6906786078","https://openalex.org/W2773549337","https://openalex.org/W2754727417","https://openalex.org/W1905522558"],"abstract_inverted_index":{"Data":[0],"selection":[1],"is":[2,15],"an":[3],"effective":[4,83],"approach":[5],"to":[6,16,25,106,131,139],"domain":[7],"adaptation":[8],"in":[9,46,76,94,134],"statistical":[10],"ma-chine":[11],"translation.":[12],"The":[13],"idea":[14],"use":[17,59],"lan-guage":[18],"models":[19,63,79],"trained":[20],"on":[21,141],"small":[22,142],"in-domain":[23,143],"text":[24],"select":[26],"similar":[27],"sentences":[28],"from":[29],"large":[30],"general-domain":[31,95],"corpora,":[32],"which":[33,49,91],"are":[34,92,117,127,137],"then":[35],"incorporated":[36],"into":[37],"the":[38,58,70,125],"training":[39],"data.":[40],"Sub-stantial":[41],"gains":[42,133],"have":[43],"been":[44],"demonstrated":[45],"previous":[47],"works,":[48],"employ":[50],"standard":[51],"n-gram":[52],"language":[53,62,78,103,115],"models.":[54],"Here,":[55],"we":[56,111],"explore":[57],"of":[60,74,101],"neural":[61,77,114],"for":[64,86,121],"data":[65,122,144],"selection.":[66],"We":[67],"hypothesize":[68],"that":[69,113],"con-tinuous":[71],"vector":[72],"representation":[73],"words":[75],"makes":[80],"them":[81],"more":[82],"than":[84],"n-grams":[85],"modeling":[87],"un-known":[88],"word":[89],"contexts,":[90],"prevalent":[93],"text.":[96],"In":[97],"a":[98],"comprehen-sive":[99],"evaluation":[100],"4":[102],"pairs":[104],"(En-glish":[105],"German,":[107],"French,":[108],"Russian,":[109],"Span-ish),":[110],"found":[112],"mod-els":[116],"indeed":[118],"viable":[119],"tools":[120],"se-lection:":[123],"while":[124],"improvements":[126],"var-ied":[128],"(i.e.":[129],"0.1":[130],"1.7":[132],"BLEU),":[135],"they":[136],"fast":[138],"train":[140],"and":[145],"can":[146],"sometimes":[147],"substantially":[148],"outper-form":[149],"conventional":[150],"n-grams.":[151],"1":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}