{"id":"https://openalex.org/W2294808479","doi":"https://doi.org/10.1109/taslp.2016.2517318","title":"Empirical Use of Information Retrieval to Build Synthetic Data for SMT Domain Adaptation","display_name":"Empirical Use of Information Retrieval to Build Synthetic Data for SMT Domain Adaptation","publication_year":2016,"publication_date":"2016-01-12","ids":{"openalex":"https://openalex.org/W2294808479","doi":"https://doi.org/10.1109/taslp.2016.2517318","mag":"2294808479"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2517318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2517318","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/A5009618709","display_name":"Sadaf Abdul-Rauf","orcid":null},"institutions":[{"id":"https://openalex.org/I6292670","display_name":"Fatima Jinnah Women University","ror":"https://ror.org/009026n40","country_code":"PK","type":"education","lineage":["https://openalex.org/I6292670"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"Sadaf Abdul-Rauf","raw_affiliation_strings":["Fatima Jinnah Women University, Rawalpindi, Pakistan"],"affiliations":[{"raw_affiliation_string":"Fatima Jinnah Women University, Rawalpindi, Pakistan","institution_ids":["https://openalex.org/I6292670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015857371","display_name":"Holger Schwenk","orcid":null},"institutions":[{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Holger Schwenk","raw_affiliation_strings":["LIUM, LUNAM University, University of Le Mans, Le Mans, France"],"affiliations":[{"raw_affiliation_string":"LIUM, LUNAM University, University of Le Mans, Le Mans, France","institution_ids":["https://openalex.org/I234216984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038292196","display_name":"Patrik Lambert","orcid":null},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Patrik Lambert","raw_affiliation_strings":["Pompeu Fabra University, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Pompeu Fabra University, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006800204","display_name":"Mohammad Nawaz","orcid":null},"institutions":[{"id":"https://openalex.org/I143719379","display_name":"Balochistan University of Information Technology, Engineering and Management Sciences","ror":"https://ror.org/01vf56d70","country_code":"PK","type":"education","lineage":["https://openalex.org/I143719379"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Mohammad Nawaz","raw_affiliation_strings":["Balochistan University Of Information Technology, Engineering, and Managment Sciences, Quetta, Pakistan"],"affiliations":[{"raw_affiliation_string":"Balochistan University Of Information Technology, Engineering, and Managment Sciences, Quetta, Pakistan","institution_ids":["https://openalex.org/I143719379"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009618709"],"corresponding_institution_ids":["https://openalex.org/I6292670"],"apc_list":null,"apc_paid":null,"fwci":2.9993,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.92513799,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"24","issue":"4","first_page":"745","last_page":"754"},"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8776470422744751},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7720916271209717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6297063231468201},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6020023822784424},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5450149178504944},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5069001317024231},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.503328263759613},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49378976225852966},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49297475814819336},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4751191735267639},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45898473262786865},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.45766690373420715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3209923505783081}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8776470422744751},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7720916271209717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6297063231468201},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6020023822784424},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5450149178504944},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5069001317024231},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.503328263759613},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49378976225852966},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49297475814819336},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4751191735267639},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45898473262786865},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.45766690373420715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3209923505783081},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2016.2517318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2517318","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":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W117861810","https://openalex.org/W132913264","https://openalex.org/W141243353","https://openalex.org/W211509693","https://openalex.org/W239287372","https://openalex.org/W1494864219","https://openalex.org/W1495370614","https://openalex.org/W1532325895","https://openalex.org/W1631260214","https://openalex.org/W1760821052","https://openalex.org/W1905522558","https://openalex.org/W1916559533","https://openalex.org/W1973152633","https://openalex.org/W1989584251","https://openalex.org/W1991522508","https://openalex.org/W1995875735","https://openalex.org/W2006969979","https://openalex.org/W2020833137","https://openalex.org/W2032175749","https://openalex.org/W2065565011","https://openalex.org/W2079145130","https://openalex.org/W2080373976","https://openalex.org/W2097333193","https://openalex.org/W2101456909","https://openalex.org/W2109394932","https://openalex.org/W2117339222","https://openalex.org/W2120445606","https://openalex.org/W2122270629","https://openalex.org/W2123635983","https://openalex.org/W2124807415","https://openalex.org/W2132001515","https://openalex.org/W2136156618","https://openalex.org/W2136477195","https://openalex.org/W2137387514","https://openalex.org/W2140460368","https://openalex.org/W2147984332","https://openalex.org/W2153653739","https://openalex.org/W2154124206","https://openalex.org/W2156985047","https://openalex.org/W2171119909","https://openalex.org/W2250851379","https://openalex.org/W2791294922","https://openalex.org/W2998215494","https://openalex.org/W4213009331","https://openalex.org/W6600880057","https://openalex.org/W6604769212","https://openalex.org/W6605403940","https://openalex.org/W6605873530","https://openalex.org/W6608606290","https://openalex.org/W6609304889","https://openalex.org/W6629627396","https://openalex.org/W6639825529","https://openalex.org/W6674571003","https://openalex.org/W6675422011","https://openalex.org/W6677294168","https://openalex.org/W6678090251","https://openalex.org/W6678210184","https://openalex.org/W6679934243","https://openalex.org/W6680264786","https://openalex.org/W6691574477"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2375873920","https://openalex.org/W3151736118","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W4362495644","https://openalex.org/W2392760275","https://openalex.org/W2756978580","https://openalex.org/W2883671469","https://openalex.org/W2359614599"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,115],"present":[4],"information":[5,40],"retrieval":[6,41],"as":[7],"a":[8,36,44,61,92],"powerful":[9],"tool":[10],"for":[11],"addressing":[12],"an":[13,55],"imperative":[14],"problem":[15],"in":[16,85],"the":[17,48,68,74,83,86,104,108],"field":[18],"of":[19,76],"statistical":[20,121],"machine":[21,122],"translation,":[22],"i.e.,":[23],"improving":[24],"translation":[25,123],"quality":[26],"when":[27],"not":[28],"enough":[29],"parallel":[30],"corpora":[31],"are":[32,116],"available.":[33],"We":[34,53,89],"devise":[35],"framework,":[37],"which":[38,65,78],"uses":[39],"to":[42,82,95,118],"create":[43],"synthetic":[45,109],"corpus":[46,110],"from":[47,103],"easily":[49],"available":[50],"monolingual":[51],"corpora.":[52],"propose":[54],"improved":[56],"unsupervised":[57],"training":[58],"approach":[59],"with":[60],"data":[62],"selection":[63],"mechanism,":[64],"selects":[66],"only":[67],"most":[69],"appropriate":[70],"sentences,":[71],"thus":[72],"reducing":[73],"amount":[75],"data,":[77],"is":[79],"less":[80],"related":[81],"domain":[84],"additional":[87],"bitext.":[88],"also":[90],"introduce":[91],"new":[93],"method":[94],"choose":[96],"sentences":[97],"based":[98],"on":[99],"their":[100],"relative":[101],"similarity/difference":[102],"query":[105],"sentence.":[106],"Using":[107],"created":[111],"by":[112],"our":[113],"method,":[114],"able":[117],"improve":[119],"state-of-the-art":[120],"systems.":[124]},"counts_by_year":[{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}