{"id":"https://openalex.org/W1908388472","doi":"https://doi.org/10.3115/v1/w14-4009","title":"Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation","display_name":"Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W1908388472","doi":"https://doi.org/10.3115/v1/w14-4009","mag":"1908388472"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-4009","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4009","pdf_url":"https://aclanthology.org/W14-4009.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-4009.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013723114","display_name":"Jean Pouget-Abadie","orcid":"https://orcid.org/0000-0003-3729-9547"},"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":"Jean Pouget-Abadie","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010465328","display_name":"Dzmitry Bahdanau","orcid":null},"institutions":[{"id":"https://openalex.org/I193619901","display_name":"Constructor University","ror":"https://ror.org/02yrs2n53","country_code":"DE","type":"education","lineage":["https://openalex.org/I193619901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dzmitry Bahdanau","raw_affiliation_strings":["Constructor University, Bremen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Constructor University, Bremen, Germany","institution_ids":["https://openalex.org/I193619901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057127344","display_name":"Bart van Merri\u00ebnboer","orcid":null},"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":"Bart van Merrienboer","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091175785","display_name":"Kyunghyun Cho","orcid":"https://orcid.org/0000-0003-1669-3211"},"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":"Kyunghyun Cho","raw_affiliation_strings":["Universit\u00e9 de Montr\u00e9al, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Montr\u00e9al, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515"},"institutions":[{"id":"https://openalex.org/I1322087612","display_name":"Alcatel Lucent (Germany)","ror":"https://ror.org/00c5mwp75","country_code":"DE","type":"company","lineage":["https://openalex.org/I1322087612"]},{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA","DE"],"is_corresponding":false,"raw_author_name":"Yoshua Bengio","raw_affiliation_strings":["Ecole Polytechnique de Montreal","Alcatel-Lucent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique de Montreal","institution_ids":["https://openalex.org/I45683168"]},{"raw_affiliation_string":"Alcatel-Lucent","institution_ids":["https://openalex.org/I1322087612"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4972,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.95677812,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"78","last_page":"85"},"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":0.9987000226974487,"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/T10759","display_name":"Translation Studies and Practices","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8152737021446228},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8107709884643555},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6971782445907593},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6698344945907593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6429392099380493},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.636471152305603},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6237746477127075},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5419981479644775},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5168678760528564},{"id":"https://openalex.org/keywords/example-based-machine-translation","display_name":"Example-based machine translation","score":0.49901270866394043},{"id":"https://openalex.org/keywords/transfer-based-machine-translation","display_name":"Transfer-based machine translation","score":0.497988224029541},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3836769461631775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8152737021446228},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8107709884643555},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6971782445907593},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6698344945907593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6429392099380493},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.636471152305603},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6237746477127075},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5419981479644775},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5168678760528564},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.49901270866394043},{"id":"https://openalex.org/C130597682","wikidata":"https://www.wikidata.org/wiki/Q6961922","display_name":"Transfer-based machine translation","level":4,"score":0.497988224029541},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3836769461631775},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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":5,"locations":[{"id":"doi:10.3115/v1/w14-4009","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4009","pdf_url":"https://aclanthology.org/W14-4009.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1409.1257","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1409.1257","pdf_url":"https://arxiv.org/pdf/1409.1257","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:1908388472","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1409.1257","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.676.2253","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.2253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/W/W14/W14-4009.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1409.1257","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1409.1257","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-4009","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4009","pdf_url":"https://aclanthology.org/W14-4009.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320320994","display_name":"Canada Research Chairs","ror":"https://ror.org/0517h6h17"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1908388472.pdf","grobid_xml":"https://content.openalex.org/works/W1908388472.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1905522558"],"related_works":["https://openalex.org/W2964335437","https://openalex.org/W2964308564","https://openalex.org/W2101105183","https://openalex.org/W2949888546","https://openalex.org/W2064675550","https://openalex.org/W1810943226","https://openalex.org/W1753482797","https://openalex.org/W2558155472","https://openalex.org/W2950635152","https://openalex.org/W2132339004","https://openalex.org/W2100664567","https://openalex.org/W3127825258","https://openalex.org/W2962780935","https://openalex.org/W3170740203","https://openalex.org/W2408292818","https://openalex.org/W2913817859","https://openalex.org/W3113527519","https://openalex.org/W2773728868","https://openalex.org/W2949509249","https://openalex.org/W2564861257"],"abstract_inverted_index":{"The":[0],"authors":[1],"of":[2],"(Cho":[3],"et":[4],"al.,":[5],"2014a)":[6],"have":[7],"shown":[8],"that":[9,53],"the":[10,59,72,77],"recently":[11],"introduced":[12],"neural":[13,60,73],"network":[14,61],"translation":[15,23,32,62,75,94],"systems":[16],"suffer":[17],"from":[18],"a":[19,39,84,90],"significant":[20,91],"drop":[21],"in":[22,93],"quality":[24,95],"when":[25],"translating":[26],"long":[27,97],"sentences,":[28],"unlike":[29],"existing":[30],"phrase-based":[31],"systems.":[33],"In":[34],"this":[35,43],"paper,":[36],"we":[37],"propose":[38],"way":[40],"to":[41,82],"address":[42],"issue":[44],"by":[45,58,71],"automatically":[46],"segmenting":[47],"an":[48],"input":[49],"sentence":[50],"into":[51],"phrases":[52],"can":[54],"be":[55],"easily":[56],"translated":[57,70,78],"model.":[63],"Once":[64],"each":[65],"segment":[66],"has":[67],"been":[68],"independently":[69],"machine":[74],"model,":[76],"clauses":[79],"are":[80],"concatenated":[81],"form":[83],"final":[85],"translation.":[86],"Empirical":[87],"results":[88],"show":[89],"improvement":[92],"for":[96],"sentences.":[98]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-06-23T13:55:30.953635","created_date":"2025-10-10T00:00:00"}