{"id":"https://openalex.org/W2807512445","doi":"https://doi.org/10.1162/coli_a_00326","title":"Feature-Based Decipherment for Machine Translation","display_name":"Feature-Based Decipherment for Machine Translation","publication_year":2018,"publication_date":"2018-06-07","ids":{"openalex":"https://openalex.org/W2807512445","doi":"https://doi.org/10.1162/coli_a_00326","mag":"2807512445"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00326","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00326","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00326","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00326","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033760431","display_name":"Iftekhar Naim","orcid":"https://orcid.org/0000-0002-2119-3273"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Iftekhar Naim","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054938572","display_name":"Parker Riley","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Parker Riley","raw_affiliation_strings":["University of Rochester, Computer Science Department"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Computer Science Department","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020945377","display_name":"Daniel Gildea","orcid":"https://orcid.org/0000-0002-7858-2624"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Daniel Gildea","raw_affiliation_strings":["University of Rochester, Computer Science Department"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Computer Science Department","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020945377","https://openalex.org/A5033760431","https://openalex.org/A5054938572"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.4887,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72221017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"44","issue":"3","first_page":"525","last_page":"546"},"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922999739646912,"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":0.9780037999153137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.706593930721283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6359118223190308},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.5320122241973877},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.52625572681427},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.500734806060791},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47032415866851807},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.46312934160232544},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.45796942710876465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4405038058757782},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3404920697212219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3347446918487549},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1302630603313446}],"concepts":[{"id":"https://openalex.org/C2778467380","wikidata":"https://www.wikidata.org/wiki/Q1345443","display_name":"Decipherment","level":2,"score":0.9780037999153137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.706593930721283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6359118223190308},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.5320122241973877},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.52625572681427},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.500734806060791},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47032415866851807},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46312934160232544},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.45796942710876465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4405038058757782},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3404920697212219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3347446918487549},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1302630603313446},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_a_00326","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00326","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00326","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:36d2bf5e9ece46c2be3554857c91789d","is_oa":true,"landing_page_url":"https://doaj.org/article/36d2bf5e9ece46c2be3554857c91789d","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 44, Iss 3, Pp 525-546 (2018)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00326","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00326","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/coli_a_00326","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2807512445.pdf","grobid_xml":"https://content.openalex.org/works/W2807512445.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W635530177","https://openalex.org/W1523199077","https://openalex.org/W1909733559","https://openalex.org/W1934041838","https://openalex.org/W2006969979","https://openalex.org/W2049633694","https://openalex.org/W2078058974","https://openalex.org/W2079656678","https://openalex.org/W2102028293","https://openalex.org/W2103042430","https://openalex.org/W2109926133","https://openalex.org/W2115367993","https://openalex.org/W2115755647","https://openalex.org/W2116064496","https://openalex.org/W2117652747","https://openalex.org/W2121745180","https://openalex.org/W2137122906","https://openalex.org/W2138247936","https://openalex.org/W2139812240","https://openalex.org/W2140406733","https://openalex.org/W2151322733","https://openalex.org/W2164746297","https://openalex.org/W2172267041","https://openalex.org/W2251257851","https://openalex.org/W2251560973","https://openalex.org/W2595840341","https://openalex.org/W2604799680","https://openalex.org/W2740132093","https://openalex.org/W2741602058","https://openalex.org/W2741609678","https://openalex.org/W2913739034","https://openalex.org/W2963088995","https://openalex.org/W4241850027","https://openalex.org/W4241982274","https://openalex.org/W4248343126"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Orthographic":[0],"similarities":[1],"across":[2],"languages":[3],"provide":[4],"a":[5,34],"strong":[6],"signal":[7],"for":[8,13,27,51],"unsupervised":[9],"probabilistic":[10],"transduction":[11],"(decipherment)":[12],"closely":[14],"related":[15],"language":[16],"pairs.":[17],"The":[18,95],"existing":[19,86],"decipherment":[20,88],"models,":[21],"however,":[22],"are":[23],"not":[24],"well":[25],"suited":[26],"exploiting":[28,91],"these":[29],"orthographic":[30,42,93],"similarities.":[31],"We":[32],"propose":[33],"log-linear":[35,54,79],"model":[36,80,96],"with":[37,81],"latent":[38],"variables":[39],"that":[40,76],"incorporates":[41],"similarity":[43],"features.":[44,94],"Maximum":[45],"likelihood":[46],"training":[47],"is":[48],"computationally":[49],"expensive":[50],"the":[52,77,85,92],"proposed":[53,78],"model.":[55],"To":[56],"address":[57],"this":[58],"challenge,":[59],"we":[60],"perform":[61],"approximate":[62],"inference":[63],"via":[64],"Markov":[65],"chain":[66],"Monte":[67],"Carlo":[68],"sampling":[69],"and":[70,102,107],"contrastive":[71,82],"divergence.":[72],"Our":[73],"results":[74],"show":[75],"divergence":[83],"outperforms":[84],"generative":[87],"models":[89],"by":[90],"both":[97],"scales":[98],"to":[99],"large":[100],"vocabularies":[101],"preserves":[103],"accuracy":[104],"in":[105],"low-":[106],"no-resource":[108],"contexts.":[109]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}