{"id":"https://openalex.org/W1973923101","doi":"https://doi.org/10.3115/1075218.1075274","title":"Improved statistical alignment models","display_name":"Improved statistical alignment models","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W1973923101","doi":"https://doi.org/10.3115/1075218.1075274","mag":"1973923101"},"language":"en","primary_location":{"id":"doi:10.3115/1075218.1075274","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075218.1075274","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1075274&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Meeting on Association for Computational Linguistics  - ACL '00","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=1075274&type=pdf","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/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"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":"Franz Josef Och","raw_affiliation_strings":["University of Technology, Aachen, Germany","University of Technology, Aachen, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]},{"raw_affiliation_string":"University of Technology, Aachen, Germany#TAB#","institution_ids":["https://openalex.org/I887968799"]}]},{"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"]},{"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","University of Technology, Aachen, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]},{"raw_affiliation_string":"University of Technology, Aachen, Germany#TAB#","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":44.5895,"has_fulltext":false,"cited_by_count":1017,"citation_normalized_percentile":{"value":0.99847325,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"440","last_page":"447"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9926000237464905,"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/ibm","display_name":"IBM","score":0.8519849181175232},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8115564584732056},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6651096343994141},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6333063840866089},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6233840584754944},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5946565270423889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5373982191085815},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.45249223709106445},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4504467248916626},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4455048143863678},{"id":"https://openalex.org/keywords/word-order","display_name":"Word order","score":0.41549259424209595},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41328150033950806},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.41180023550987244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3886690139770508},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.35674619674682617},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3368954062461853},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09463730454444885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08272349834442139}],"concepts":[{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.8519849181175232},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115564584732056},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6651096343994141},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6333063840866089},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6233840584754944},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5946565270423889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5373982191085815},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.45249223709106445},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4504467248916626},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4455048143863678},{"id":"https://openalex.org/C70777604","wikidata":"https://www.wikidata.org/wiki/Q257885","display_name":"Word order","level":2,"score":0.41549259424209595},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41328150033950806},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.41180023550987244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3886690139770508},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.35674619674682617},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3368954062461853},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09463730454444885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08272349834442139},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/1075218.1075274","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075218.1075274","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1075274&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Meeting on Association for Computational Linguistics  - ACL '00","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.9666","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.9666","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/P00/P00-1056.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.37.5030","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.37.5030","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/ACL00.ps","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:111464","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/111464","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 2000 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora : held in conjunction with the 38. Annual Meeting of the Association for Computational Linguistics ; 7.-8.10.2000, Hong Kong University of Science and Technology (HUST), Hong Kong / ACL 2000. Sponsored by Behavior Design Corporation.. / Sch\u00fctze, H. [u.a.] Hrsg<br/>Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora : held in conjunction with the 38. Annual Meeting of the Association for Computational Linguistics, Hong Kong, Hong Kong, 2000-10-07 - 2000-10-08","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.3115/1075218.1075274","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1075218.1075274","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=1075274&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th Annual Meeting on Association for Computational Linguistics  - ACL '00","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","score":0.5600000023841858,"display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1973923101.pdf","grobid_xml":"https://content.openalex.org/works/W1973923101.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W136130055","https://openalex.org/W1525706028","https://openalex.org/W1575431606","https://openalex.org/W1811404221","https://openalex.org/W1979102019","https://openalex.org/W2006969979","https://openalex.org/W2030750105","https://openalex.org/W2038698865","https://openalex.org/W3104029765"],"related_works":["https://openalex.org/W2593596363","https://openalex.org/W2096837052","https://openalex.org/W2100780576","https://openalex.org/W2100295236","https://openalex.org/W2379938888","https://openalex.org/W2116722627","https://openalex.org/W2127464923","https://openalex.org/W2143650221","https://openalex.org/W3044198794","https://openalex.org/W2369168983"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,42],"present":[4,33],"and":[5,29,66],"compare":[6],"various":[7,30],"single-word":[8],"based":[9],"alignment":[10,21,25,50],"models":[11,61,78],"for":[12],"statistical":[13],"machine":[14],"translation.":[15],"We":[16,32,58],"discuss":[17],"the":[18,23,44,47,76],"five":[19],"IBM":[20],"models,":[22],"Hidden-Markov":[24],"model,":[26],"smoothing":[27],"techniques":[28],"modifications.":[31],"different":[34],"methods":[35],"to":[36,52,71,86],"combine":[37],"alignments.":[38],"As":[39],"evaluation":[40],"criterion":[41],"use":[43],"quality":[45],"of":[46],"resulting":[48],"Viterbi":[49],"compared":[51],"a":[53,63,67],"manually":[54],"produced":[55],"reference":[56],"alignment.":[57],"show":[59],"that":[60],"with":[62],"first-order":[64],"dependence":[65],"fertility":[68],"model":[69],"lead":[70],"significantly":[72],"better":[73],"results":[74],"than":[75],"simple":[77],"IBM-1":[79],"or":[80],"IBM-2,":[81],"which":[82],"are":[83],"not":[84],"able":[85],"go":[87],"beyond":[88],"zero-order":[89],"dependencies.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":33},{"year":2015,"cited_by_count":39},{"year":2014,"cited_by_count":52},{"year":2013,"cited_by_count":64},{"year":2012,"cited_by_count":75}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}