{"id":"https://openalex.org/W2111329418","doi":"https://doi.org/10.3115/1218955.1218978","title":"Statistical machine translation with word- and sentence-aligned parallel corpora","display_name":"Statistical machine translation with word- and sentence-aligned parallel corpora","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2111329418","doi":"https://doi.org/10.3115/1218955.1218978","mag":"2111329418"},"language":"en","primary_location":{"id":"doi:10.3115/1218955.1218978","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218978","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1218978","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics  - ACL '04","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/10.3115/1218955.1218978","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068508539","display_name":"Chris Callison-Burch","orcid":"https://orcid.org/0000-0001-8196-1943"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Chris Callison-Burch","raw_affiliation_strings":["University of Edinburgh, Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012252833","display_name":"David Talbot","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Talbot","raw_affiliation_strings":["University of Edinburgh, Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058230090","display_name":"Miles Osborne","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Miles Osborne","raw_affiliation_strings":["University of Edinburgh, Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068508539"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":10.1668,"has_fulltext":true,"cited_by_count":92,"citation_normalized_percentile":{"value":0.98065182,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"175","last_page":"es"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9854000210762024,"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":0.8205595016479492},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7666710615158081},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7614707946777344},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7609779834747314},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.741540253162384},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6914228796958923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.635059118270874},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6172303557395935},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.5952081084251404},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5264447927474976},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.49689820408821106},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4414912462234497},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.42333298921585083},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4136987328529358},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41245806217193604},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09119769930839539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205595016479492},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7666710615158081},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7614707946777344},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7609779834747314},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.741540253162384},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6914228796958923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635059118270874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6172303557395935},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.5952081084251404},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5264447927474976},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.49689820408821106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4414912462234497},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.42333298921585083},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4136987328529358},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41245806217193604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09119769930839539},{"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/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/1218955.1218978","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218978","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1218978","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics  - ACL '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.127.4109","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.127.4109","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/acl2004/main/pdf/238_pdf_2-col.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.6.3881","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.6.3881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cogsci.ed.ac.uk/~osborne/papers/acl04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.3776","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.3776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-csli.stanford.edu/~ccb/publications/smt-with-word-and-sentence-aligned-parallel-corpora.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1218955.1218978","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1218955.1218978","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1218955.1218978","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics  - ACL '04","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2111329418.pdf","grobid_xml":"https://content.openalex.org/works/W2111329418.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1558805185","https://openalex.org/W1811404221","https://openalex.org/W2006969979","https://openalex.org/W2047295649","https://openalex.org/W2049633694","https://openalex.org/W2097089247","https://openalex.org/W2101105183","https://openalex.org/W2102616831","https://openalex.org/W2141532438","https://openalex.org/W2153653739","https://openalex.org/W2156985047","https://openalex.org/W4238317531","https://openalex.org/W4241645538"],"related_works":["https://openalex.org/W2786253471","https://openalex.org/W2990400634","https://openalex.org/W2463396630","https://openalex.org/W3175595715","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W783305165","https://openalex.org/W2990352702","https://openalex.org/W4293584592","https://openalex.org/W2986030184"],"abstract_inverted_index":{"The":[0],"parameters":[1],"of":[2,24,44,100],"statistical":[3],"translation":[4,22],"models":[5,26,47,63],"are":[6],"typically":[7],"estimated":[8],"from":[9],"sentence-aligned":[10,66,103],"parallel":[11],"corpora.":[12],"We":[13,94],"show":[14],"that":[15],"significant":[16],"improvements":[17],"in":[18,78],"the":[19,41,45,54,61,69,79,98,106],"alignment":[20,49,80],"and":[21,52,83],"quality":[23],"such":[25],"can":[27],"be":[28],"achieved":[29],"by":[30],"additionally":[31],"including":[32],"word-aligned":[33,101],"data":[34,71,104],"during":[35],"training.":[36],"Incorporating":[37],"word-level":[38],"alignments":[39],"into":[40],"parameter":[42],"estimation":[43],"IBM":[46],"reduces":[48],"error":[50,81],"rate":[51,82],"increases":[53],"Bleu":[55,86],"score":[56,87],"when":[57],"compared":[58],"to":[59,102],"training":[60,92],"same":[62],"only":[64],"on":[65],"data.":[67],"On":[68],"Verbmobil":[70],"set,":[72],"we":[73],"attain":[74],"a":[75,84],"38%":[76],"reduction":[77],"higher":[85],"with":[88],"half":[89],"as":[90],"many":[91],"examples.":[93],"discuss":[95],"how":[96],"varying":[97],"ratio":[99],"affects":[105],"expected":[107],"performance":[108],"gain.":[109]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}