{"id":"https://openalex.org/W2803739890","doi":"https://doi.org/10.1109/taslp.2018.2837223","title":"Sentence Selection and Weighting for Neural Machine Translation Domain Adaptation","display_name":"Sentence Selection and Weighting for Neural Machine Translation Domain Adaptation","publication_year":2018,"publication_date":"2018-05-16","ids":{"openalex":"https://openalex.org/W2803739890","doi":"https://doi.org/10.1109/taslp.2018.2837223","mag":"2803739890"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2837223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2837223","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/A5100431149","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0001-8007-2503"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021667085","display_name":"Masao Utiyama","orcid":"https://orcid.org/0000-0003-1111-9245"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masao Utiyama","raw_affiliation_strings":["Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081198426","display_name":"Andrew Finch","orcid":"https://orcid.org/0000-0002-7067-7098"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Andrew Finch","raw_affiliation_strings":["Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005411806","display_name":"Lemao Liu","orcid":"https://orcid.org/0000-0003-3804-5768"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lemao Liu","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006323375","display_name":"Kehai Chen","orcid":"https://orcid.org/0000-0002-4346-7618"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kehai Chen","raw_affiliation_strings":["Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033318800","display_name":"Eiichiro Sumita","orcid":"https://orcid.org/0000-0002-1028-4399"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eiichiro Sumita","raw_affiliation_strings":["Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100431149"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":6.1896,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.97085887,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"26","issue":"10","first_page":"1727","last_page":"1741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9842000007629395,"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":0.8295260071754456},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7764467000961304},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7689106464385986},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7121338844299316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6664783358573914},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6103779077529907},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6090130805969238},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5549846887588501},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4825645983219147},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.41157642006874084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3827827274799347},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3359696865081787},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08710834383964539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295260071754456},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7764467000961304},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7689106464385986},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7121338844299316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6664783358573914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6103779077529907},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6090130805969238},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5549846887588501},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4825645983219147},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.41157642006874084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3827827274799347},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3359696865081787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08710834383964539},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2837223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2837223","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","display_name":"Quality Education","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":142,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W157748702","https://openalex.org/W222053410","https://openalex.org/W353957520","https://openalex.org/W1205016396","https://openalex.org/W1731081199","https://openalex.org/W1848260265","https://openalex.org/W1902237438","https://openalex.org/W1905522558","https://openalex.org/W2005874308","https://openalex.org/W2020073413","https://openalex.org/W2032558547","https://openalex.org/W2034368206","https://openalex.org/W2051203581","https://openalex.org/W2062291443","https://openalex.org/W2095669743","https://openalex.org/W2100664567","https://openalex.org/W2101105183","https://openalex.org/W2106595396","https://openalex.org/W2111362445","https://openalex.org/W2115056464","https://openalex.org/W2115410424","https://openalex.org/W2117278770","https://openalex.org/W2124807415","https://openalex.org/W2129659804","https://openalex.org/W2133564696","https://openalex.org/W2133622676","https://openalex.org/W2137698233","https://openalex.org/W2147262247","https://openalex.org/W2155173537","https://openalex.org/W2157331557","https://openalex.org/W2157830631","https://openalex.org/W2181672650","https://openalex.org/W2223152534","https://openalex.org/W2250314498","https://openalex.org/W2251335508","https://openalex.org/W2251536071","https://openalex.org/W2261339088","https://openalex.org/W2340221426","https://openalex.org/W2350508517","https://openalex.org/W2466062786","https://openalex.org/W2499786410","https://openalex.org/W2522770641","https://openalex.org/W2567571499","https://openalex.org/W2578927531","https://openalex.org/W2581863816","https://openalex.org/W2584268338","https://openalex.org/W2593768305","https://openalex.org/W2594229957","https://openalex.org/W2601324753","https://openalex.org/W2609232568","https://openalex.org/W2618250040","https://openalex.org/W2620623908","https://openalex.org/W2740132093","https://openalex.org/W2740553716","https://openalex.org/W2740718109","https://openalex.org/W2740743644","https://openalex.org/W2741787148","https://openalex.org/W2744813330","https://openalex.org/W2750588180","https://openalex.org/W2755989362","https://openalex.org/W2756978580","https://openalex.org/W2757592053","https://openalex.org/W2760452458","https://openalex.org/W2760705958","https://openalex.org/W2767699072","https://openalex.org/W2767899794","https://openalex.org/W2788768841","https://openalex.org/W2905927205","https://openalex.org/W2950635152","https://openalex.org/W2952030765","https://openalex.org/W2962897020","https://openalex.org/W2963122608","https://openalex.org/W2963188492","https://openalex.org/W2963233928","https://openalex.org/W2963260202","https://openalex.org/W2963338195","https://openalex.org/W2963355640","https://openalex.org/W2963366389","https://openalex.org/W2963506925","https://openalex.org/W2963602293","https://openalex.org/W2963661177","https://openalex.org/W2963713328","https://openalex.org/W2963841178","https://openalex.org/W2963932569","https://openalex.org/W2963937700","https://openalex.org/W2964028737","https://openalex.org/W2964057616","https://openalex.org/W2964308564","https://openalex.org/W3015703505","https://openalex.org/W3093419064","https://openalex.org/W3203347510","https://openalex.org/W3204130541","https://openalex.org/W3204406378","https://openalex.org/W3208011254","https://openalex.org/W4237826793","https://openalex.org/W4297664233","https://openalex.org/W4298393544","https://openalex.org/W4300996741","https://openalex.org/W6600284362","https://openalex.org/W6608792757","https://openalex.org/W6628006141","https://openalex.org/W6637618735","https://openalex.org/W6639113993","https://openalex.org/W6639825529","https://openalex.org/W6674388476","https://openalex.org/W6676115256","https://openalex.org/W6677017890","https://openalex.org/W6677069268","https://openalex.org/W6677328538","https://openalex.org/W6679424467","https://openalex.org/W6679434410","https://openalex.org/W6679961620","https://openalex.org/W6680325970","https://openalex.org/W6681547378","https://openalex.org/W6683224722","https://openalex.org/W6691387978","https://openalex.org/W6692595355","https://openalex.org/W6704224172","https://openalex.org/W6705584953","https://openalex.org/W6724106704","https://openalex.org/W6726922386","https://openalex.org/W6730161283","https://openalex.org/W6731349619","https://openalex.org/W6731988802","https://openalex.org/W6732277000","https://openalex.org/W6733037173","https://openalex.org/W6735368890","https://openalex.org/W6738313283","https://openalex.org/W6739073796","https://openalex.org/W6743473661","https://openalex.org/W6744577730","https://openalex.org/W6745388339","https://openalex.org/W6745620410","https://openalex.org/W6746141323","https://openalex.org/W6746434100","https://openalex.org/W6748805638","https://openalex.org/W6757517122","https://openalex.org/W6802243670","https://openalex.org/W6802318714","https://openalex.org/W6802817094","https://openalex.org/W6802820818"],"related_works":["https://openalex.org/W2841102378","https://openalex.org/W4383678258","https://openalex.org/W4385571464","https://openalex.org/W4379539336","https://openalex.org/W2140460368","https://openalex.org/W2963897095","https://openalex.org/W4385572994","https://openalex.org/W4307783854","https://openalex.org/W2887289680","https://openalex.org/W2805394970"],"abstract_inverted_index":{"Neural":[0],"machine":[1,9,67],"translation":[2,10,25,38,229],"(NMT)":[3],"has":[4],"been":[5,75],"prominent":[6],"in":[7,13,154,177,223],"many":[8],"tasks.":[11],"However,":[12],"some":[14],"domain-specific":[15],"tasks,":[16],"only":[17,76],"the":[18,34,37,51,64,105,113,127,147,163,174,183,202,210,242,251,255],"corpora":[19,29],"from":[20],"similar":[21],"domains":[22],"can":[23,248],"improve":[24,250],"performance.":[26],"If":[27],"out-of-domain":[28,121],"are":[30,47,61,124,221],"directly":[31],"added":[32],"into":[33],"in-domain":[35,128],"corpus,":[36],"performance":[39],"may":[40],"even":[41],"degrade.":[42],"Therefore,":[43],"domain":[44,53,59,71,86,89,102,140,184,203,211],"adaptation":[45,60],"techniques":[46],"essential":[48],"to":[49,119,126,145,161,172,200],"solve":[50,173],"NMT":[52,70,101,151,169,180,252],"problem.":[54],"Most":[55],"existing":[56,256],"methods":[57,160,220,247],"for":[58,63,98],"designed":[62],"conventional":[65],"phrase-based":[66],"translation.":[68],"For":[69],"adaptation,":[72],"there":[73],"have":[74,95],"a":[77,178,195,234],"few":[78],"studies":[79],"on":[80,226],"topics":[81],"such":[82],"as":[83],"fine":[84],"tuning,":[85],"tags,":[87],"and":[88,112,142,166,188,208,215,233,245],"features.":[90],"In":[91],"this":[92],"paper,":[93],"we":[94,131,156,193],"four":[96],"goals":[97],"sentence":[99,108,114,134,138,164,197,243],"level":[100],"adaptation.":[103],"First,":[104],"NMT's":[106],"internal":[107],"embedding":[109,115],"is":[110,117],"exploited":[111],"similarity":[116],"used":[118],"select":[120],"sentences":[122],"that":[123,241],"close":[125],"corpus.":[129],"Second,":[130],"propose":[132,157],"three":[133],"weighting":[135,167,198,246],"methods,":[136],"i.e.,":[137],"weighting,":[139,141,144],"batch":[143],"balance":[146,201],"data":[148,190,207],"distribution":[149],"during":[150,168],"training.":[152,170],"Third,":[153],"addition,":[155],"dynamic":[158],"training":[159,187,206,214],"adjust":[162],"selection":[165,244],"Fourth,":[171],"multidomain":[175,196,235],"problem":[176],"real-world":[179],"scenario":[181],"where":[182],"distributions":[185,204,212],"of":[186,205,213],"testing":[189,216],"often":[191],"mismatch,":[192],"proposed":[194,219],"method":[199],"match":[209],"data.":[217],"The":[218],"evaluated":[222],"international":[224],"workshop":[225],"spoken":[227],"language":[228],"(IWSLT)":[230],"English-to-French/German":[231],"tasks":[232],"English-to-French":[236],"task.":[237],"Empirical":[238],"results":[239],"show":[240],"significantly":[249],"performance,":[253],"outperforming":[254],"baselines.":[257]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}