{"id":"https://openalex.org/W2154124206","doi":"https://doi.org/10.3115/1073083.1073133","title":"Discriminative training and maximum entropy models for statistical machine translation","display_name":"Discriminative training and maximum entropy models for statistical machine translation","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2154124206","doi":"https://doi.org/10.3115/1073083.1073133","mag":"2154124206"},"language":"en","primary_location":{"id":"doi:10.3115/1073083.1073133","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073133","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073133","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073133","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046457818","display_name":"Franz Josef Och","orcid":null},"institutions":[{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Franz Josef Och","raw_affiliation_strings":["University of Technology, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"University of Technology, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["University of Technology, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"University of Technology, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046457818"],"corresponding_institution_ids":["https://openalex.org/I99977706"],"apc_list":null,"apc_paid":null,"fwci":28.9137,"has_fulltext":true,"cited_by_count":1043,"citation_normalized_percentile":{"value":0.99628586,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"295","last_page":"295"},"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":0.9991000294685364,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.968500018119812,"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/machine-translation","display_name":"Machine translation","score":0.8813798427581787},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8273473978042603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.822479248046875},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.7185829877853394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7030710577964783},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6376217603683472},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6301673650741577},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.5172046422958374},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5104595422744751},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5077482461929321},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4741767644882202},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4688348174095154},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4510759711265564},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.4249136447906494},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42015600204467773},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33501189947128296}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8813798427581787},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8273473978042603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822479248046875},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.7185829877853394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7030710577964783},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6376217603683472},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6301673650741577},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.5172046422958374},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5104595422744751},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5077482461929321},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4741767644882202},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4688348174095154},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4510759711265564},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.4249136447906494},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42015600204467773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33501189947128296},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.3115/1073083.1073133","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073133","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073133","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.18.4454","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.18.4454","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/PostScript/InterneArbeiten/Och_Disc_Train_and_MaxEnt_Stat_Machine_Translation_ACL2002.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.8830","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.8830","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/P/P02/P02-1038.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.8005","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.8005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.toronto.edu/~gh/Courses/2528/Readings/Och+Ney.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.573.1406","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.573.1406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-rohan.sdsu.edu/~gawron/mt_plus/readings/max_ent/me_smt_och_acl02.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.9602","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.9602","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/Colleagues/och/ACL02.ps","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:113539","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/113539","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Proceedings of the conference, 40th annual meeting of the Association for Computational Linguistics : Philadelphia, [6 - 13] July 2002, University of Pennsylvania, Philadelphia, Pennsylvania / jointly hosted by the North American chapter of the ACL<br/>40. annual meeting of the Association for Computational Linguistics, Philadelphia, PA, USA, 2002-07-06 - 2002-07-13","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.3115/1073083.1073133","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073083.1073133","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073083.1073133","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics  - ACL '02","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2154124206.pdf","grobid_xml":"https://content.openalex.org/works/W2154124206.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1517947178","https://openalex.org/W1518357715","https://openalex.org/W1529616844","https://openalex.org/W1562694524","https://openalex.org/W1585396714","https://openalex.org/W1877570817","https://openalex.org/W1979102019","https://openalex.org/W2001792610","https://openalex.org/W2006969979","https://openalex.org/W2095743640","https://openalex.org/W2096175520","https://openalex.org/W2101105183","https://openalex.org/W2117428648","https://openalex.org/W2129545859","https://openalex.org/W2500011979","https://openalex.org/W4251285258"],"related_works":["https://openalex.org/W1504625892","https://openalex.org/W2166769824","https://openalex.org/W2047632477","https://openalex.org/W2012202551","https://openalex.org/W2163454936","https://openalex.org/W318813979","https://openalex.org/W2018123871","https://openalex.org/W1482794692","https://openalex.org/W2106477919","https://openalex.org/W2394860946"],"abstract_inverted_index":{"We":[0,68],"present":[1],"a":[2,25,54,71],"framework":[3],"for":[4],"statistical":[5,73],"machine":[6,56,74],"translation":[7,57,75],"of":[8],"natural":[9],"languages":[10],"based":[11],"on":[12,38],"direct":[13],"maximum":[14],"entropy":[15],"models,":[16],"which":[17,36],"contains":[18],"the":[19,39,43],"widely":[20],"used":[21],"source-channel":[22],"approach":[23,52],"as":[24,33],"special":[26],"case.":[27],"All":[28],"knowledge":[29],"sources":[30],"are":[31],"treated":[32],"feature":[34,66],"functions,":[35],"depend":[37],"source":[40],"language":[41,45],"sentence,":[42],"target":[44],"sentence":[46],"and":[47],"possible":[48],"hidden":[49],"variables.":[50],"This":[51],"allows":[53],"baseline":[55,72],"system":[58,76],"to":[59],"be":[60],"extended":[61],"easily":[62],"by":[63],"adding":[64],"new":[65],"functions.":[67],"show":[69],"that":[70],"is":[77],"significantly":[78],"improved":[79],"using":[80],"this":[81],"approach.":[82]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":38},{"year":2017,"cited_by_count":36},{"year":2016,"cited_by_count":50},{"year":2015,"cited_by_count":51},{"year":2014,"cited_by_count":57},{"year":2013,"cited_by_count":45},{"year":2012,"cited_by_count":80}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}