{"id":"https://openalex.org/W2156985047","doi":"https://doi.org/10.1162/089120103321337421","title":"A Systematic Comparison of Various Statistical Alignment Models","display_name":"A Systematic Comparison of Various Statistical Alignment Models","publication_year":2003,"publication_date":"2003-03-01","ids":{"openalex":"https://openalex.org/W2156985047","doi":"https://doi.org/10.1162/089120103321337421","mag":"2156985047"},"language":"en","primary_location":{"id":"doi:10.1162/089120103321337421","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103321337421","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120103321337421","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"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":"bronze","oa_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120103321337421","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046457818","display_name":"Franz Josef Och","orcid":null},"institutions":[{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Franz Josef Och","raw_affiliation_strings":["University of Southern California, Information Science Institute (USC/ISI), 4029 Via Marina, Suite 1001, Marina del Rey, CA 90292"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Information Science Institute (USC/ISI), 4029 Via Marina, Suite 1001, Marina del Rey, CA 90292","institution_ids":["https://openalex.org/I2801204180"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"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":"Hermann Ney","raw_affiliation_strings":["RWTH Aachen, Lehrstuhl f\u00fcr Informatik VI, Computer Science Department, RWTH Aachen-University of Technology, D-52056 Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen, Lehrstuhl f\u00fcr Informatik VI, Computer Science Department, RWTH Aachen-University of Technology, D-52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046457818"],"corresponding_institution_ids":["https://openalex.org/I2801204180"],"apc_list":null,"apc_paid":null,"fwci":130.7019,"has_fulltext":true,"cited_by_count":3925,"citation_normalized_percentile":{"value":0.99985387,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":"1","first_page":"19","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9901999831199646,"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/T12031","display_name":"Speech and dialogue systems","score":0.9623000025749207,"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/computer-science","display_name":"Computer science","score":0.8173164129257202},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6674555540084839},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.65367591381073},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5704584717750549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5550951361656189},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4912678599357605},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.43587762117385864},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4358011484146118},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4325132369995117},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.42161184549331665},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38481462001800537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13724061846733093},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09789970517158508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173164129257202},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6674555540084839},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.65367591381073},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5704584717750549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5550951361656189},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4912678599357605},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.43587762117385864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4358011484146118},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4325132369995117},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.42161184549331665},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38481462001800537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13724061846733093},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09789970517158508},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1162/089120103321337421","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103321337421","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120103321337421","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.1288","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.1288","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/J/J03/J03-1002.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.323.9974","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.323.9974","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/word/read/comp_stat_alignment_och_ney_cl03.pdf","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:fc29d3681d3940118946d75259112098","is_oa":false,"landing_page_url":"https://doaj.org/article/fc29d3681d3940118946d75259112098","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 29, Iss 1 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/089120103321337421","is_oa":true,"landing_page_url":"https://doi.org/10.1162/089120103321337421","pdf_url":"http://www.mitpressjournals.org/doi/pdf/10.1162/089120103321337421","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7777770697","display_name":"1999 Language Engineering Workshop for Students and Professionals:  Integrating Research and Education (WS99)","funder_award_id":"9820687","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320324232","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2156985047.pdf","grobid_xml":"https://content.openalex.org/works/W2156985047.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W47415966","https://openalex.org/W87890863","https://openalex.org/W1480519300","https://openalex.org/W1517947178","https://openalex.org/W1538023239","https://openalex.org/W1543107604","https://openalex.org/W1555286493","https://openalex.org/W1575431606","https://openalex.org/W1811404221","https://openalex.org/W1916559533","https://openalex.org/W1979102019","https://openalex.org/W1987869189","https://openalex.org/W1991348388","https://openalex.org/W1994919150","https://openalex.org/W2006969979","https://openalex.org/W2016630033","https://openalex.org/W2030750105","https://openalex.org/W2038698865","https://openalex.org/W2047603832","https://openalex.org/W2049633694","https://openalex.org/W2071991030","https://openalex.org/W2107551411","https://openalex.org/W2116316001","https://openalex.org/W2119168550","https://openalex.org/W2134627713","https://openalex.org/W2138753018","https://openalex.org/W2139403546","https://openalex.org/W2140830074","https://openalex.org/W2146418175","https://openalex.org/W2151525026","https://openalex.org/W2158703834","https://openalex.org/W2196555355","https://openalex.org/W2396590899","https://openalex.org/W2422872931","https://openalex.org/W3021520429","https://openalex.org/W3088420009","https://openalex.org/W4231741839","https://openalex.org/W4241850027","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2114811871","https://openalex.org/W3177062893","https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W1539050421","https://openalex.org/W1068348394","https://openalex.org/W1563147278","https://openalex.org/W2022141716","https://openalex.org/W2165288811","https://openalex.org/W988067430"],"abstract_inverted_index":{"We":[0,15,54,90,104],"present":[1,55,155],"and":[2,28,38,99,118,139],"compare":[3],"various":[4,110,125],"methods":[5,57],"for":[6,58,160],"computing":[7],"word":[8,60],"alignments":[9,61],"using":[10],"statistical":[11,41,68,115],"or":[12],"heuristic":[13,47,149],"models.":[14,70,150],"consider":[16],"the":[17,31,51,76,79,92,95,100,152,161],"five":[18],"alignment":[19,34,69,82,116,133,162],"models":[20,42,48,93,134,163],"presented":[21],"in":[22],"Brown,":[23],"Della":[24,26],"Pietra,":[25,27],"Mercer":[29],"(1993),":[30],"hidden":[32],"Markov":[33],"model,":[35],"smoothing":[36],"techniques,":[37],"refinements.":[39],"These":[40],"are":[43],"compared":[44,83],"with":[45,135],"two":[46],"based":[49],"on":[50,94,121],"Dice":[52],"coefficient.":[53],"different":[56],"combining":[59],"to":[62,84],"perform":[63,105],"a":[64,85,106,136,140],"symmetrization":[65],"of":[66,78,109,113,124],"directed":[67],"As":[71],"evaluation":[72],"criterion,":[73],"we":[74,154],"use":[75],"quality":[77],"resulting":[80],"Viterbi":[81],"manually":[86],"produced":[87],"reference":[88],"alignment.":[89],"evaluate":[91,119],"German-English":[96],"Verbmobil":[97],"task":[98],"French-English":[101],"Hansards":[102],"task.":[103],"detailed":[107],"analysis":[108],"design":[111],"decisions":[112],"our":[114],"system":[117],"these":[120],"training":[122,158],"corpora":[123],"sizes.":[126],"An":[127],"important":[128],"result":[129],"is":[130],"that":[131],"refined":[132],"first-order":[137],"dependence":[138],"fertility":[141],"model":[142],"yield":[143],"significantly":[144],"better":[145],"results":[146],"than":[147],"simple":[148],"In":[151],"Appendix,":[153],"an":[156],"efficient":[157],"algorithm":[159],"presented.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":58},{"year":2022,"cited_by_count":65},{"year":2021,"cited_by_count":144},{"year":2020,"cited_by_count":129},{"year":2019,"cited_by_count":154},{"year":2018,"cited_by_count":160},{"year":2017,"cited_by_count":201},{"year":2016,"cited_by_count":256},{"year":2015,"cited_by_count":261},{"year":2014,"cited_by_count":323},{"year":2013,"cited_by_count":289},{"year":2012,"cited_by_count":322}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}