{"id":"https://openalex.org/W2159872955","doi":"https://doi.org/10.21437/interspeech.2009-156","title":"Iterative sentence-pair extraction from quasi-parallel corpora for machine translation","display_name":"Iterative sentence-pair extraction from quasi-parallel corpora for machine translation","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W2159872955","doi":"https://doi.org/10.21437/interspeech.2009-156","mag":"2159872955"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-156","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"conference-paper","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/A5072875068","display_name":"Ruhi Sarikaya","orcid":"https://orcid.org/0000-0003-2676-2831"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R. Sarikaya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110215786","display_name":"Sameer Maskey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sameer Maskey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029387407","display_name":"Ronghui Zhang","orcid":"https://orcid.org/0000-0001-6107-4044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R. Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041659867","display_name":"Ea-Ee Jan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ea-Ee Jan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050710249","display_name":"Dingdong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043396055","display_name":"Salim Roukos","orcid":"https://orcid.org/0000-0003-2140-4349"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Roukos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"432","last_page":"435"},"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/T10759","display_name":"Translation Studies and Practices","score":0.9905999898910522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8868347406387329},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7216290235519409},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7208142876625061},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6678537726402283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.653079628944397},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.579097330570221},{"id":"https://openalex.org/keywords/evaluation-of-machine-translation","display_name":"Evaluation of machine translation","score":0.5418323874473572},{"id":"https://openalex.org/keywords/pairing","display_name":"Pairing","score":0.5270586013793945},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5217978954315186},{"id":"https://openalex.org/keywords/carry","display_name":"Carry (investment)","score":0.5049830079078674},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.4877934753894806},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42472606897354126},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.42140302062034607},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.3312036097049713},{"id":"https://openalex.org/keywords/machine-translation-software-usability","display_name":"Machine translation software usability","score":0.14669322967529297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8868347406387329},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7216290235519409},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7208142876625061},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6678537726402283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.653079628944397},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.579097330570221},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.5418323874473572},{"id":"https://openalex.org/C14103023","wikidata":"https://www.wikidata.org/wiki/Q11681459","display_name":"Pairing","level":3,"score":0.5270586013793945},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5217978954315186},{"id":"https://openalex.org/C2776299755","wikidata":"https://www.wikidata.org/wiki/Q432449","display_name":"Carry (investment)","level":2,"score":0.5049830079078674},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.4877934753894806},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42472606897354126},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.42140302062034607},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.3312036097049713},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.14669322967529297},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C54101563","wikidata":"https://www.wikidata.org/wiki/Q124131","display_name":"Superconductivity","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-156","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.6497","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.6497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.columbia.edu/%7Esmaskey/papers/sent_select_mt.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1497763703","https://openalex.org/W1533246198","https://openalex.org/W1819903106","https://openalex.org/W1988012253","https://openalex.org/W2101105183","https://openalex.org/W2101746535","https://openalex.org/W2104103102","https://openalex.org/W2107695330","https://openalex.org/W2153653739","https://openalex.org/W2156985047"],"related_works":["https://openalex.org/W3204448004","https://openalex.org/W2962780935","https://openalex.org/W2122287718","https://openalex.org/W2532807140","https://openalex.org/W193726211","https://openalex.org/W2740094425","https://openalex.org/W3196981096","https://openalex.org/W4378619223","https://openalex.org/W2587602790","https://openalex.org/W3152052241"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"parallel":[3,87],"data":[4,125,147,165],"extraction":[5],"from":[6,89],"the":[7,53,56,63,66,90,107,116,123,131,145,152],"quasi\u2013parallel":[8],"corpora":[9],"generated":[10],"in":[11,31,69,82],"a":[12,70,76],"crowd-sourcing":[13],"project":[14],"where":[15],"ordinary":[16],"people":[17],"watch":[18],"tv":[19],"shows":[20,126],"and":[21,23,42,59,85,110],"movies":[22],"transcribe/translate":[24],"what":[25],"they":[26,35],"hear,":[27],"creating":[28],"document":[29,72,100],"pools":[30],"different":[32],"languages.":[33],"Since":[34],"do":[36],"not":[37,48],"have":[38],"guidelines":[39],"for":[40,78,137],"naming":[41],"performing":[43],"translations,":[44],"it":[45],"is":[46],"often":[47],"clear":[49],"which":[50,60],"documents":[51,81],"are":[52,62],"translations":[54,64],"of":[55,65,96,106,122,130],"same":[57],"show/movie":[58],"sentences":[61,88,133],"each":[67],"other":[68],"given":[71],"pair.":[73],"We":[74],"introduce":[75],"method":[77,94],"automatically":[79],"pairing":[80],"two":[83],"languages":[84],"extracting":[86],"paired":[91,108],"documents.":[92],"The":[93],"consists":[95],"three":[97],"steps:":[98],"i)":[99],"pairing,":[101],"ii)":[102],"sentence":[103,117],"pair":[104,118],"alignment":[105],"documents,":[109],"iii)":[111],"context":[112],"extrapolation":[113],"to":[114],"boost":[115],"coverage.":[119],"Human":[120],"evaluation":[121],"extracted":[124,132,146],"that":[127,143],"95":[128],"%":[129],"carry":[134],"useful":[135],"information":[136],"translation.":[138],"Experimental":[139],"results":[140],"also":[141],"show":[142],"using":[144],"provides":[148],"significant":[149],"gains":[150],"over":[151],"baseline":[153],"statistical":[154],"machine":[155,169],"translation":[156,170],"system":[157],"built":[158],"with":[159],"manually":[160],"annotated":[161],"data.":[162],"Index":[163],"Terms:":[164],"extraction,":[166],"comparable":[167],"data,":[168]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}