{"id":"https://openalex.org/W2251560973","doi":"https://doi.org/10.3115/v1/d14-1061","title":"Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation","display_name":"Beyond Parallel Data: Joint Word Alignment and Decipherment Improves Machine Translation","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251560973","doi":"https://doi.org/10.3115/v1/d14-1061","mag":"2251560973"},"language":"en","primary_location":{"id":"doi:10.3115/v1/d14-1061","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1061","pdf_url":"https://aclanthology.org/D14-1061.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D14-1061.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015808183","display_name":"Qing Dou","orcid":"https://orcid.org/0009-0002-9104-4967"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I903300897","display_name":"Southern States University","ror":"https://ror.org/01b0j0m34","country_code":"US","type":"education","lineage":["https://openalex.org/I903300897"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Dou","raw_affiliation_strings":["Information Sciences Institute Department of Computer Science University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute Department of Computer Science University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I903300897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103024730","display_name":"Ashish Vaswani","orcid":"https://orcid.org/0000-0002-7794-2085"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I903300897","display_name":"Southern States University","ror":"https://ror.org/01b0j0m34","country_code":"US","type":"education","lineage":["https://openalex.org/I903300897"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Vaswani","raw_affiliation_strings":["Information Sciences Institute Department of Computer Science University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute Department of Computer Science University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I903300897"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106821597","display_name":"Kevin Knight","orcid":"https://orcid.org/0000-0001-9117-1718"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I903300897","display_name":"Southern States University","ror":"https://ror.org/01b0j0m34","country_code":"US","type":"education","lineage":["https://openalex.org/I903300897"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Knight","raw_affiliation_strings":["Information Sciences Institute Department of Computer Science University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute Department of Computer Science University of Southern California","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I903300897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"557","last_page":"565"},"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/T13629","display_name":"Text Readability and Simplification","score":0.9966999888420105,"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/decipherment","display_name":"Decipherment","score":0.9934982061386108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8334271311759949},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8280508518218994},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6727758646011353},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6683953404426575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6595720052719116},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6536949276924133},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.49324172735214233},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4685654938220978},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3720666170120239},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0808953046798706},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07903382182121277}],"concepts":[{"id":"https://openalex.org/C2778467380","wikidata":"https://www.wikidata.org/wiki/Q1345443","display_name":"Decipherment","level":2,"score":0.9934982061386108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8334271311759949},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8280508518218994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6727758646011353},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6683953404426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6595720052719116},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6536949276924133},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.49324172735214233},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4685654938220978},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3720666170120239},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0808953046798706},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07903382182121277},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/v1/d14-1061","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1061","pdf_url":"https://aclanthology.org/D14-1061.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.567.8050","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.567.8050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isi.edu/natural-language/mt/dou-vaswani-knight-14.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.665.1155","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.665.1155","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/D/D14/D14-1061.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.683.4123","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.683.4123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://emnlp2014.org/papers/pdf/EMNLP2014061.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/d14-1061","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1061","pdf_url":"https://aclanthology.org/D14-1061.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1520207243","display_name":"RI: Medium: Deciphering Natural Language (DECIPHER)","funder_award_id":"0904684","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251560973.pdf","grobid_xml":"https://content.openalex.org/works/W2251560973.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W38126138","https://openalex.org/W149643677","https://openalex.org/W161217653","https://openalex.org/W1508577659","https://openalex.org/W1632114991","https://openalex.org/W2006969979","https://openalex.org/W2008184426","https://openalex.org/W2038698865","https://openalex.org/W2041232209","https://openalex.org/W2049633694","https://openalex.org/W2079442239","https://openalex.org/W2084277454","https://openalex.org/W2102028293","https://openalex.org/W2103042430","https://openalex.org/W2110974939","https://openalex.org/W2121415745","https://openalex.org/W2121745180","https://openalex.org/W2124807415","https://openalex.org/W2131698806","https://openalex.org/W2136346830","https://openalex.org/W2139812240","https://openalex.org/W2140406733","https://openalex.org/W2146574666","https://openalex.org/W2151942821","https://openalex.org/W2160097208","https://openalex.org/W2160721348","https://openalex.org/W2162302090","https://openalex.org/W2169360026","https://openalex.org/W2172267041","https://openalex.org/W2172268343","https://openalex.org/W2250229103","https://openalex.org/W2250640401","https://openalex.org/W2252053087","https://openalex.org/W2595715041","https://openalex.org/W2600716915","https://openalex.org/W3037265734"],"related_works":["https://openalex.org/W2353267881","https://openalex.org/W2087163944","https://openalex.org/W2313343935","https://openalex.org/W2123799460","https://openalex.org/W4249394616","https://openalex.org/W2011818515","https://openalex.org/W4243114292","https://openalex.org/W4294940244","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"Inspired":[0],"by":[1],"previous":[2],"work,":[3],"where":[4,59],"decipherment":[5,22],"is":[6,67],"used":[7],"to":[8,17,31,38,54,77],"improve":[9,55],"machine":[10,57],"translation,":[11,58],"we":[12,72],"propose":[13],"a":[14,24,61,81],"new":[15],"idea":[16],"combine":[18],"word":[19],"alignment":[20],"and":[21],"into":[23],"single":[25],"learning":[26],"process.":[27],"We":[28,50],"use":[29],"EM":[30],"estimate":[32],"the":[33,40,47],"model":[34],"parameters,":[35],"not":[36],"only":[37,60],"maximize":[39],"probability":[41],"of":[42,64,75],"parallel":[43,65],"corpus,":[44],"but":[45],"also":[46],"monolingual":[48],"corpus.":[49],"apply":[51],"our":[52,70],"approach":[53],"Malagasy-English":[56],"small":[62],"amount":[63],"data":[66],"available.":[68],"In":[69],"experiments,":[71],"observe":[73],"gains":[74],"0.9":[76],"2.1":[78],"Bleu":[79],"over":[80],"strong":[82],"baseline.":[83]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}