{"id":"https://openalex.org/W2396575863","doi":null,"title":"Combining Translation and Language Model Scoring for Domain-Specific Data Filtering","display_name":"Combining Translation and Language Model Scoring for Domain-Specific Data Filtering","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2396575863","mag":"2396575863"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.6501","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.6501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/publications/download/761/Mansour-IWSLT-2011.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/A5070002963","display_name":"Saab Mansour","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saab Mansour","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067263769","display_name":"Joern Wuebker","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joern Wuebker","raw_affiliation_strings":["RWTH Aachen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4644,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95296974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"222","last_page":"229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0012000000569969416,"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":0.0005000000237487257,"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":0.8180000185966492},{"id":"https://openalex.org/keywords/filtering","display_name":"filtering","score":0.5260000228881836},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.8560000061988831},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"cross-entropy","score":0.7450000047683716},{"id":"https://openalex.org/keywords/perplexity","display_name":"perplexity","score":0.9449999928474426},{"id":"https://openalex.org/keywords/domain-specific-data","display_name":"domain-specific data","score":0.4659999907016754},{"id":"https://openalex.org/keywords/arabic-english-translation","display_name":"Arabic-English translation","score":0.6949999928474426},{"id":"https://openalex.org/keywords/english-french-translation","display_name":"English-French translation","score":0.9660000205039978},{"id":"https://openalex.org/keywords/ted-talks","display_name":"TED Talks","score":0.8349999785423279},{"id":"https://openalex.org/keywords/vocabulary-reduction","display_name":"vocabulary reduction","score":0.6769999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001852035522461},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6694055199623108},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.6482436656951904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6361180543899536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6110785007476807},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.568035364151001},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5403968691825867},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5360980033874512},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5312362313270569},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.5193608403205872},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3496131896972656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32696402072906494},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0920783281326294},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/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}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.6501","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.6501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/publications/download/761/Mansour-IWSLT-2011.pdf","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:127767","doi":null,"is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/search?p=id:%22RWTH-CONV-197967%22","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISWLT 2011 : Proceedings of the International Workshop on Spoken Language Translation ; December 08 and 09, 2011, San Francisco, USA / ed. by Marcello Federico ...<br/>International Workshop on Spoken Language Translation, ISWLT 2011, San Francisco, CA, USA, 2011-12-08 - 2011-12-09","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:2396575863","doi":null,"is_oa":false,"landing_page_url":"http://www-i6.informatik.rwth-aachen.de/publications/download/761/Mansour-IWSLT-2011.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306514703","display_name":"IWSLT","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"IWSLT","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":17,"referenced_works":["https://openalex.org/W23077562","https://openalex.org/W222053410","https://openalex.org/W1848260265","https://openalex.org/W1905522558","https://openalex.org/W1974967573","https://openalex.org/W2006969979","https://openalex.org/W2101105183","https://openalex.org/W2115410424","https://openalex.org/W2117278770","https://openalex.org/W2117339222","https://openalex.org/W2124807415","https://openalex.org/W2126784811","https://openalex.org/W2136477195","https://openalex.org/W2137387514","https://openalex.org/W2146574666","https://openalex.org/W2149327368","https://openalex.org/W2156985047"],"related_works":["https://openalex.org/W2533887179","https://openalex.org/W2133622676","https://openalex.org/W3171488001","https://openalex.org/W7100812987","https://openalex.org/W2171519600","https://openalex.org/W2132001515","https://openalex.org/W2374569281","https://openalex.org/W3203347510","https://openalex.org/W2182115895","https://openalex.org/W40379961"],"abstract_inverted_index":{"The":[0],"increasing":[1],"popularity":[2],"of":[3,13,66,182,202],"statistical":[4],"machine":[5],"translation":[6,14,77,129,154],"(SMT)":[7],"systems":[8],"is":[9,213],"introducing":[10],"new":[11,43],"domains":[12],"that":[15,93],"need":[16],"to":[17,32,54,152,159,208],"be":[18,30,97],"tackled.":[19],"As":[20,178],"many":[21],"resources":[22],"are":[23,197],"already":[24,83],"available,":[25],"domain":[26],"adaptation":[27,47,183],"methods":[28],"can":[29],"applied":[31,84],"utilize":[33],"these":[34],"recourses":[35],"in":[36],"the":[37,42,51,71,76,131,153,166,175,186],"most":[38],"beneficial":[39],"way":[40],"for":[41,62,89,99,106],"domain.":[44],"We":[45,58,91,109,124],"explore":[46],"via":[48,184],"filtering,":[49,101,143,165,185],"using":[50],"crossentropy":[52],"scores":[53],"discard":[55],"irrelevant":[56],"sentences.":[57],"focus":[59],"on":[60,116],"filtering":[61,113],"two":[63,127],"important":[64],"components":[65],"an":[67],"SMT":[68,189],"system,":[69],"namely":[70],"language":[72],"model":[73,78],"(LM)":[74],"and":[75,120,133,193],"(TM).":[79],"Previous":[80],"work":[81],"has":[82],"LM":[85,94,100,121,142],"cross-entropy":[86,95,122],"based":[87,115],"scoring":[88],"filtering.":[90,108],"argue":[92],"might":[96],"appropriate":[98],"but":[102,171],"not":[103],"as":[104],"much":[105],"TM":[107,119,164],"develop":[110],"a":[111,117,179,200],"novel":[112],"approach":[114],"combined":[118,167],"scores.":[123],"experiment":[125],"with":[126,156],"large-scale":[128],"tasks,":[130],"Arabicto-English":[132],"English-to-French":[134],"IWSLT":[135],"2011":[136],"TED":[137],"Talks":[138],"MT":[139],"tasks.":[140],"For":[141,163],"we":[144],"achieve":[145],"strong":[146],"perplexity":[147],"improvements":[148,157,173],"which":[149],"carry":[150],"over":[151,174],"quality":[155],"up":[158,207],"+0.4":[160],"%":[161,210],"BLEU.":[162],"method":[168],"achieves":[169],"small":[170],"consistent":[172],"standalone":[176],"methods.":[177],"side":[180],"effect":[181],"fully":[187],"fledged":[188],"system":[190],"vocabulary":[191],"size":[192,196],"phrase":[194],"table":[195],"reduced":[198],"by":[199],"factor":[201],"at":[203],"least":[204],"2":[205],"while":[206],"+0.6":[209],"BLEU":[211],"improvement":[212],"observed.":[214],"1.":[215]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2016-06-24T00:00:00"}