{"id":"https://openalex.org/W2978265966","doi":"https://doi.org/10.18653/v1/w19-8620","title":"On Leveraging the Visual Modality for Neural Machine Translation","display_name":"On Leveraging the Visual Modality for Neural Machine Translation","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2978265966","doi":"https://doi.org/10.18653/v1/w19-8620","mag":"2978265966"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-8620","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8620","pdf_url":"https://www.aclweb.org/anthology/W19-8620.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 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-8620.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035694997","display_name":"Vikas Raunak","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":"Vikas Raunak","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083042393","display_name":"Sang Keun Choe","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":"Sang Keun Choe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112757890","display_name":"Quanyang Lu","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":"Quanyang Lu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018343158","display_name":"Yi Xu","orcid":"https://orcid.org/0000-0003-2126-6054"},"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":"Yi Xu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"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":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":0.2187,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53059533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.794448971748352},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.779242753982544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6411533951759338},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6277188062667847},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6134876012802124},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5835800170898438},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.553850531578064},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5293582081794739},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4273887872695923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3222101628780365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794448971748352},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.779242753982544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6411533951759338},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6277188062667847},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6134876012802124},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5835800170898438},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.553850531578064},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5293582081794739},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4273887872695923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3222101628780365},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w19-8620","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8620","pdf_url":"https://www.aclweb.org/anthology/W19-8620.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 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.02754","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.02754","pdf_url":"https://arxiv.org/pdf/1910.02754","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},{"id":"mag:2978265966","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.02754.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.1910.02754","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.02754","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-8620","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8620","pdf_url":"https://www.aclweb.org/anthology/W19-8620.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 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2978265966.pdf","grobid_xml":"https://content.openalex.org/works/W2978265966.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1664311846","https://openalex.org/W1902237438","https://openalex.org/W2130942839","https://openalex.org/W2252238675","https://openalex.org/W2513263213","https://openalex.org/W2525778437","https://openalex.org/W2549139847","https://openalex.org/W2553522418","https://openalex.org/W2609160544","https://openalex.org/W2885185669","https://openalex.org/W2896234464","https://openalex.org/W2910092637","https://openalex.org/W2924679246","https://openalex.org/W2962784628","https://openalex.org/W2964073004","https://openalex.org/W3042657922"],"related_works":["https://openalex.org/W2995427493","https://openalex.org/W2997084499","https://openalex.org/W3035421790","https://openalex.org/W2920195923","https://openalex.org/W2509593407","https://openalex.org/W2462993019","https://openalex.org/W3090930194","https://openalex.org/W2622442300","https://openalex.org/W2904518532","https://openalex.org/W3198170507","https://openalex.org/W809730796","https://openalex.org/W3185121530","https://openalex.org/W3091387667","https://openalex.org/W3009205145","https://openalex.org/W2970409072","https://openalex.org/W2912070261","https://openalex.org/W2939633001","https://openalex.org/W3204548263","https://openalex.org/W3158495294","https://openalex.org/W2163282847"],"abstract_inverted_index":{"Leveraging":[0],"the":[1,23,31,38,48,52,105,114,156,159,184,189,192,197],"visual":[2,108,137,193],"modality":[3],"effectively":[4],"for":[5,56,145,148],"Neural":[6],"Machine":[7,72],"Translation":[8,73],"(NMT)":[9],"remains":[10],"an":[11],"open":[12],"problem":[13],"in":[14,166,206],"computational":[15],"linguistics.":[16],"Recently,":[17],"Caglayan":[18],"et":[19],"al.":[20],"posit":[21,135],"that":[22,136,186],"observed":[24],"gains":[25,129],"are":[26],"limited":[27],"mainly":[28],"due":[29],"to":[30,103,154,203],"very":[32],"simple,":[33],"short,":[34],"repetitive":[35],"sentences":[36],"of":[37,99,107,113,191,199],"Multi30k":[39,86],"dataset":[40,45],"(the":[41],"only":[42,127],"multimodal":[43,71],"MT":[44],"available":[46],"at":[47,110,162,183],"time),":[49],"which":[50,77,100,201],"renders":[51],"source":[53],"text":[54],"sufficient":[55],"context.":[57,122],"In":[58],"this":[59,64,170],"work,":[60],"we":[61,124],"further":[62],"investigate":[63],"hypothesis":[65],"on":[66],"a":[67],"new":[68],"large":[69],"scale":[70],"(MMT)":[74],"dataset,":[75],"How2,":[76],"has":[78],"1.57":[79],"times":[80],"longer":[81],"mean":[82],"sentence":[83],"length":[84,198],"than":[85,196],"and":[87,92,134,176],"no":[88],"repetition.":[89],"We":[90,168],"propose":[91],"evaluate":[93],"three":[94],"novel":[95],"fusion":[96],"techniques,":[97],"each":[98],"is":[101,188],"designed":[102],"ensure":[104],"utilization":[106],"context":[109,133],"different":[111],"stages":[112],"Sequence-to-Sequence":[115],"transduction":[116],"pipeline,":[117],"even":[118],"under":[119,130],"full":[120,131],"linguistic":[121,132],"However,":[123],"still":[125],"obtain":[126],"marginal":[128],"embeddings":[138,194],"extracted":[139],"from":[140],"deep":[141],"vision":[142],"models":[143],"(ResNet":[144],"Multi30k,":[146],"ResNext":[147],"How2)":[149],"do":[150],"not":[151],"lend":[152],"themselves":[153],"increasing":[155],"discriminativeness":[157],"between":[158],"vocabulary":[160],"elements":[161],"token":[163],"level":[164],"prediction":[165],"NMT.":[167],"demonstrate":[169],"qualitatively":[171],"by":[172],"analyzing":[173],"attention":[174],"distribution":[175],"quantitatively":[177],"through":[178],"Principal":[179],"Component":[180],"Analysis,":[181],"arriving":[182],"conclusion":[185],"it":[187],"quality":[190],"rather":[195],"sentences,":[200],"need":[202],"be":[204],"improved":[205],"existing":[207],"MMT":[208],"datasets.":[209]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}