{"id":"https://openalex.org/W2103863416","doi":"https://doi.org/10.3115/1073012.1073039","title":"Refined lexicon models for statistical machine translation using a maximum entropy approach","display_name":"Refined lexicon models for statistical machine translation using a maximum entropy approach","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2103863416","doi":"https://doi.org/10.3115/1073012.1073039","mag":"2103863416"},"language":"en","primary_location":{"id":"doi:10.3115/1073012.1073039","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073012.1073039","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073012.1073039","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th Annual Meeting on Association for Computational Linguistics  - ACL '01","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/10.3115/1073012.1073039","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002824408","display_name":"Ismael Garc\u00eda-Varea","orcid":"https://orcid.org/0000-0003-3451-7852"},"institutions":[{"id":"https://openalex.org/I79189158","display_name":"University of Castilla-La Mancha","ror":"https://ror.org/05r78ng12","country_code":"ES","type":"education","lineage":["https://openalex.org/I79189158"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ismael Garc\u00eda Varea","raw_affiliation_strings":["Univ. de Castilla-La Mancha, Albacete, Spain","University of Castilla-La Mancha#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. de Castilla-La Mancha, Albacete, Spain","institution_ids":["https://openalex.org/I79189158"]},{"raw_affiliation_string":"University of Castilla-La Mancha#TAB#","institution_ids":["https://openalex.org/I79189158"]}]},{"author_position":"middle","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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Franz J. Och","raw_affiliation_strings":["Lehrstuhl f\u00fcr Inf. VI, RWTH Aachen, Ahornstr., Aachen, Germany","[Rwth Aachen University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehrstuhl f\u00fcr Inf. VI, RWTH Aachen, Ahornstr., Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"[Rwth Aachen University]","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","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":["Lehrstuhl f\u00fcr Inf. VI, RWTH Aachen, Ahornstr., Aachen, Germany","Lehrstuhl f\u00fcr Inf. VI, RWTH Aachen, Ahornstr., Aachen, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehrstuhl f\u00fcr Inf. VI, RWTH Aachen, Ahornstr., Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Lehrstuhl f\u00fcr Inf. VI, RWTH Aachen, Ahornstr., Aachen, Germany#TAB#","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020181962","display_name":"Francisco Casacuberta","orcid":"https://orcid.org/0000-0002-8497-5598"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francisco Casacuberta","raw_affiliation_strings":["Inst. Tecn. de Inf. (UPV), Valencia, Spain","Polytechnic University of Valencia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. Tecn. de Inf. (UPV), Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]},{"raw_affiliation_string":"Polytechnic University of Valencia","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9204,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94976401,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"204","last_page":"211"},"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":0.9998000264167786,"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":0.9898999929428101,"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/machine-translation","display_name":"Machine translation","score":0.8610713481903076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7986769676208496},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7714498043060303},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.695184051990509},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.6936330795288086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6915832161903381},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.6897784471511841},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6850175857543945},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5399911403656006},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.47593238949775696},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.44123750925064087},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33356428146362305},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3303610682487488}],"concepts":[{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8610713481903076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986769676208496},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7714498043060303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.695184051990509},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.6936330795288086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6915832161903381},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.6897784471511841},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6850175857543945},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5399911403656006},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.47593238949775696},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.44123750925064087},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33356428146362305},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3303610682487488},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3115/1073012.1073039","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073012.1073039","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073012.1073039","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th Annual Meeting on Association for Computational Linguistics  - ACL '01","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.16.3382","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.16.3382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iti.upv.es/~prhlt/PAPERS/papers01-02/2001/Garcia-Varea01a.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.183.5709","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.183.5709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://prhlt.iti.es/papers/2001/Garcia-Varea01a.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.8763","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.8763","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/P01/P01-1027.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.20.8847","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.8847","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/me_acl2001.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.9360","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.9360","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/Paper_2001/Varea_LexModelsWITHMaxEnt_ACL_2001.ps","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1073012.1073039","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1073012.1073039","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1073012.1073039","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th Annual Meeting on Association for Computational Linguistics  - ACL '01","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2103863416.pdf","grobid_xml":"https://content.openalex.org/works/W2103863416.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1518357715","https://openalex.org/W1600680149","https://openalex.org/W1973923101","https://openalex.org/W1996903695","https://openalex.org/W2006969979","https://openalex.org/W2012511220","https://openalex.org/W2065174184","https://openalex.org/W2083460949","https://openalex.org/W2095743640","https://openalex.org/W2096175520","https://openalex.org/W2107551411","https://openalex.org/W2116532807","https://openalex.org/W2150234123","https://openalex.org/W2158164089","https://openalex.org/W2160842254","https://openalex.org/W2169424935","https://openalex.org/W2422872931","https://openalex.org/W3104029765","https://openalex.org/W4230173372","https://openalex.org/W4301730641"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W4287323699","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2902731467","https://openalex.org/W2787311093"],"abstract_inverted_index":{"Typically,":[0],"the":[1,40,82,112],"lexicon":[2],"models":[3],"used":[4],"in":[5,25,104],"statistical":[6,41,63],"machine":[7,64],"translation":[8,65,83,105],"systems":[9],"do":[10],"not":[11],"include":[12],"any":[13],"kind":[14],"of":[15,59,81,91],"linguistic":[16],"or":[17],"contextual":[18],"information,":[19],"which":[20],"often":[21],"leads":[22],"to":[23,34,44,55,73],"problems":[24],"performing":[26],"a":[27,62,89],"correct":[28],"word":[29],"sense":[30],"disambiguation.":[31],"One":[32],"way":[33],"deal":[35],"with":[36],"this":[37,50,57],"problem":[38],"within":[39,61],"framework":[42],"is":[43,71],"use":[45,56],"maximum":[46,96],"entropy":[47,97],"methods.":[48],"In":[49,85],"paper,":[51],"we":[52,87],"present":[53],"how":[54],"type":[58],"information":[60],"system.":[66],"We":[67],"show":[68],"that":[69],"it":[70],"possible":[72],"significantly":[74],"decrease":[75],"training":[76],"and":[77,99],"test":[78],"corpus":[79],"perplexity":[80],"models.":[84],"addition,":[86],"perform":[88],"rescoring":[90],"N-Best":[92],"lists":[93],"using":[94],"our":[95],"model":[98],"thereby":[100],"yield":[101],"an":[102],"improvement":[103],"quality.":[106],"Experimental":[107],"results":[108],"are":[109],"presented":[110],"on":[111],"so-called":[113],"\"Verbmobil":[114],"Task\".":[115]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}