{"id":"https://openalex.org/W2989476591","doi":"https://doi.org/10.18653/v1/d19-5621","title":"A Margin-based Loss with Synthetic Negative Samples for Continuous-output Machine Translation","display_name":"A Margin-based Loss with Synthetic Negative Samples for Continuous-output Machine Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2989476591","doi":"https://doi.org/10.18653/v1/d19-5621","mag":"2989476591"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-5621","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5621","pdf_url":"https://www.aclweb.org/anthology/D19-5621.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 the 3rd Workshop on Neural Generation and Translation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D19-5621.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085218914","display_name":"Gayatri Bhat","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gayatri Bhat","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102123110","display_name":"Sachin Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sachin Kumar","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062910836","display_name":"Yulia Tsvetkov","orcid":"https://orcid.org/0000-0002-4634-7128"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yulia Tsvetkov","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"205"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9896000027656555,"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/margin","display_name":"Margin (machine learning)","score":0.9033061265945435},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6970884203910828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6318614482879639},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5787720680236816},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5083791613578796},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4698407053947449},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45487770438194275},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44220292568206787},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42916440963745117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4233793318271637},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38707858324050903},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3406063914299011},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3081687092781067},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2908085584640503}],"concepts":[{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.9033061265945435},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6970884203910828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6318614482879639},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5787720680236816},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5083791613578796},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4698407053947449},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45487770438194275},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44220292568206787},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42916440963745117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4233793318271637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38707858324050903},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3406063914299011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3081687092781067},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2908085584640503},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":1,"locations":[{"id":"doi:10.18653/v1/d19-5621","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5621","pdf_url":"https://www.aclweb.org/anthology/D19-5621.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 the 3rd Workshop on Neural Generation and Translation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d19-5621","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-5621","pdf_url":"https://www.aclweb.org/anthology/D19-5621.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 the 3rd Workshop on Neural Generation and Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2989476591.pdf","grobid_xml":"https://content.openalex.org/works/W2989476591.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W21006490","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1899794420","https://openalex.org/W1902237438","https://openalex.org/W1938755728","https://openalex.org/W2101105183","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2137807925","https://openalex.org/W2138621090","https://openalex.org/W2153579005","https://openalex.org/W2158899491","https://openalex.org/W2242874043","https://openalex.org/W2250646737","https://openalex.org/W2493916176","https://openalex.org/W2539338396","https://openalex.org/W2737608545","https://openalex.org/W2755957574","https://openalex.org/W2888844359","https://openalex.org/W2889574253","https://openalex.org/W2899682268","https://openalex.org/W2904683980","https://openalex.org/W2905927205","https://openalex.org/W2951559648","https://openalex.org/W2952230511","https://openalex.org/W2953830716","https://openalex.org/W2962779279","https://openalex.org/W2962784628","https://openalex.org/W2962902328","https://openalex.org/W2963118869","https://openalex.org/W2963421945","https://openalex.org/W2963656735","https://openalex.org/W2963702081","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W3099206234","https://openalex.org/W4294170691","https://openalex.org/W4299579390"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W4226420367","https://openalex.org/W2982889384","https://openalex.org/W4226227567","https://openalex.org/W2971218105","https://openalex.org/W3010284783","https://openalex.org/W4287113729","https://openalex.org/W3173314472","https://openalex.org/W4386598483"],"abstract_inverted_index":{"Neural":[0],"models":[1,26],"that":[2,67,98,112],"eliminate":[3],"the":[4,49,76],"softmax":[5],"bottleneck":[6],"by":[7,30,42],"generating":[8],"word":[9],"embeddings":[10,36,80],"(rather":[11],"than":[12,105],"multinomial":[13],"distributions":[14,40],"over":[15,119],"a":[16,63,69,93],"vocabulary)":[17],"attain":[18],"faster":[19],"training":[20],"with":[21],"fewer":[22],"learnable":[23],"parameters.":[24],"These":[25],"are":[27],"currently":[28],"trained":[29],"maximizing":[31],"densities":[32],"of":[33,51],"pretrained":[34],"target":[35,79],"under":[37],"von":[38],"Mises-Fisher":[39],"parameterized":[41],"corresponding":[43],"model-predicted":[44],"embeddings.":[45],"This":[46],"work":[47],"explores":[48],"utility":[50],"margin-based":[52],"loss":[53,66,85],"functions":[54],"in":[55,126],"optimizing":[56],"such":[57],"models.":[58],"We":[59],"present":[60],"syn-margin":[61],"loss,":[62],"novel":[64],"marginbased":[65,107,124],"uses":[68],"synthetic":[70],"negative":[71],"sample":[72],"constructed":[73],"from":[74],"only":[75],"predicted":[77],"and":[78,90,103,122],"at":[81],"every":[82],"step.":[83],"The":[84],"is":[86,100],"efficient":[87],"to":[88,96],"compute,":[89],"we":[91,110],"use":[92],"geometric":[94],"analysis":[95],"argue":[97],"it":[99],"more":[101],"consistent":[102],"interpretable":[104],"other":[106],"losses.":[108],"Empirically,":[109],"find":[111],"synmargin":[113],"provides":[114],"small":[115],"but":[116],"significant":[117],"improvements":[118],"both":[120],"vMF":[121],"standard":[123],"losses":[125],"continuous-output":[127],"neural":[128],"machine":[129],"translation.":[130]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}