{"id":"https://openalex.org/W2117745860","doi":"https://doi.org/10.3115/1220575.1220670","title":"Translating with non-contiguous phrases","display_name":"Translating with non-contiguous phrases","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2117745860","doi":"https://doi.org/10.3115/1220575.1220670","mag":"2117745860"},"language":"en","primary_location":{"id":"doi:10.3115/1220575.1220670","doi":"https://doi.org/10.3115/1220575.1220670","is_oa":false,"landing_page_url":"https://doi.org/10.3115/1220575.1220670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Michel Simard","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michel Simard","raw_affiliation_strings":["Xerox Research Centre Europe","Xerox Research Centre Europe#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe","institution_ids":[]},{"raw_affiliation_string":"Xerox Research Centre Europe#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004751764","display_name":"Nicola Cancedda","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicola Cancedda","raw_affiliation_strings":["Xerox Research Centre Europe","Xerox Research Centre Europe#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe","institution_ids":[]},{"raw_affiliation_string":"Xerox Research Centre Europe#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044059871","display_name":"Bruno Cavestro","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bruno Cavestro","raw_affiliation_strings":["Xerox Research Centre Europe","Xerox Research Centre Europe#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe","institution_ids":[]},{"raw_affiliation_string":"Xerox Research Centre Europe#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059468860","display_name":"Marc Dymetman","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Dymetman","raw_affiliation_strings":["Xerox Research Centre Europe","Xerox Research Centre Europe#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe","institution_ids":[]},{"raw_affiliation_string":"Xerox Research Centre Europe#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014352159","display_name":"\u00c9ric Gaussier","orcid":"https://orcid.org/0000-0002-8858-3233","observed_orcids":["https://orcid.org/0000-0002-8858-3233"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Gaussier","raw_affiliation_strings":["Xerox Research Centre Europe","Xerox Research Centre Europe#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe","institution_ids":[]},{"raw_affiliation_string":"Xerox Research Centre Europe#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065257553","display_name":"Cyril Goutte","orcid":"https://orcid.org/0000-0003-4939-6555","observed_orcids":["https://orcid.org/0000-0003-4939-6555"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cyril Goutte","raw_affiliation_strings":["Xerox Research Centre Europe","Xerox Research Centre Europe#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe","institution_ids":[]},{"raw_affiliation_string":"Xerox Research Centre Europe#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105125515","display_name":"Kenji Yamada","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kenji Yamada","raw_affiliation_strings":["Xerox Research Centre Europe","Xerox Research Centre Europe#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xerox Research Centre Europe","institution_ids":[]},{"raw_affiliation_string":"Xerox Research Centre Europe#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034154991","display_name":"Philippe Langlais","orcid":"https://orcid.org/0000-0002-7319-1595","observed_orcids":["https://orcid.org/0000-0002-7319-1595"]},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Philippe Langlais","raw_affiliation_strings":["RALI/DIRO Universit\u00e9 de Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RALI/DIRO Universit\u00e9 de Montr\u00e9al","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064940734","display_name":"Arne Mauser","orcid":null,"observed_orcids":[]},"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":"Arne Mauser","raw_affiliation_strings":["RWTH Aachen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.7485,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.9613777,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"755","last_page":"762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.000699999975040555,"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":9.999999747378752e-05,"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/phrase-based-machine-translation","display_name":"phrase-based statistical machine translation","score":0.9559999704360962},{"id":"https://openalex.org/keywords/beam-search-decoding","display_name":"beam search decoding","score":0.8550000190734863}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8738915324211121},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7903007864952087},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7777903079986572},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7167389392852783},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6760416030883789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6658902168273926},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6496715545654297},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5758060216903687},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.49628907442092896},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4662771224975586},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.41070249676704407},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39403608441352844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11696410179138184},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.060620129108428955},{"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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.0},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3115/1220575.1220670","doi":"https://doi.org/10.3115/1220575.1220670","is_oa":false,"landing_page_url":"https://doi.org/10.3115/1220575.1220670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.136.6584","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.136.6584","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/h/h05/h05-1095.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.550.9900","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.550.9900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mt-archive.info/HLT-EMNLP-2005-Simard.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.555.8575","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.555.8575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sifnos.ilsp.gr/RevealThis/Publications/Publications/emnlp05.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.1175","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.1175","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.xrce.xerox.com/Publications/Attachments/2005-042/simard05translating.pdf","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:113699","doi":null,"is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/113699","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,"listed_in":[],"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 / HLT/EMNLP 2005, Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing : 6 - 8 October 2005, Vancouver, British Columbia, Canada / [general chair: Raymond J. Mooney]<br/>Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Vancouver, British Columbia, Canada, 2005-10-06 - 2005-10-08","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W24102868","https://openalex.org/W54534146","https://openalex.org/W1509476036","https://openalex.org/W1517947178","https://openalex.org/W1869993023","https://openalex.org/W1973923101","https://openalex.org/W2006969979","https://openalex.org/W2032772856","https://openalex.org/W2078861931","https://openalex.org/W2101105183","https://openalex.org/W2108540317","https://openalex.org/W2111798208","https://openalex.org/W2119168550","https://openalex.org/W2135399222","https://openalex.org/W2139403546","https://openalex.org/W2146574666","https://openalex.org/W2152263452","https://openalex.org/W2156985047","https://openalex.org/W2161792612"],"related_works":["https://openalex.org/W2096462592","https://openalex.org/W87191003","https://openalex.org/W7098573639","https://openalex.org/W2215355985","https://openalex.org/W1736600331","https://openalex.org/W7099450175","https://openalex.org/W7095577006","https://openalex.org/W2346086519","https://openalex.org/W2152263452","https://openalex.org/W2356514692"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,24,43,66],"phrase-based":[4],"statistical":[5,30],"machine":[6],"translation":[7,31,51],"method,":[8],"based":[9,46],"on":[10,47],"non-contiguous":[11],"phrases,":[12,39],"i.e.":[13],"phrases":[14,22],"with":[15,55],"gaps.":[16],"A":[17,29],"method":[18,45,78],"for":[19],"producing":[20],"such":[21,38],"from":[23,83],"word-aligned":[25],"corpora":[26],"is":[27,33],"proposed.":[28],"model":[32],"also":[34],"presented":[35],"that":[36,73],"deals":[37],"as":[40,42,53],"well":[41],"training":[44,85],"the":[48,56,76,84],"maximization":[49],"of":[50,65],"accuracy,":[52],"measured":[54],"NIST":[57],"evaluation":[58],"metric.":[59],"Translations":[60],"are":[61,71],"produced":[62],"by":[63],"means":[64],"beam-search":[67],"decoder.":[68],"Experimental":[69],"results":[70],"presented,":[72],"demonstrate":[74],"how":[75],"proposed":[77],"allows":[79],"to":[80],"better":[81],"generalize":[82],"data.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":8}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}