{"id":"https://openalex.org/W1486723856","doi":"https://doi.org/10.3115/v1/n15-1016","title":"Combining Language and Vision with a Multimodal Skip-gram Model","display_name":"Combining Language and Vision with a Multimodal Skip-gram Model","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1486723856","doi":"https://doi.org/10.3115/v1/n15-1016","mag":"1486723856"},"language":"en","primary_location":{"id":"doi:10.3115/v1/n15-1016","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/n15-1016","pdf_url":"https://doi.org/10.3115/v1/n15-1016","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/n15-1016","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042659302","display_name":"Angeliki Lazaridou","orcid":"https://orcid.org/0000-0002-5857-474X"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Angeliki Lazaridou","raw_affiliation_strings":["University of Trento"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nghia The Pham","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nghia The Pham","raw_affiliation_strings":["University of Trento"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Trento","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":null,"display_name":"Marco Baroni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Baroni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.7394,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.97799692,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9927999973297119,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9904999732971191,"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/n-gram","display_name":"n-gram","score":0.8457457423210144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7887136936187744},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6919374465942383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6297741532325745},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6070109009742737},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.581946611404419},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5443068146705627},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49737027287483215},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4747103750705719},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4223382771015167},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.4189102351665497},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21737855672836304},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0961391031742096}],"concepts":[{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.8457457423210144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887136936187744},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6919374465942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6297741532325745},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6070109009742737},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.581946611404419},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5443068146705627},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49737027287483215},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4747103750705719},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4223382771015167},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.4189102351665497},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21737855672836304},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0961391031742096},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3115/v1/n15-1016","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/n15-1016","pdf_url":"https://doi.org/10.3115/v1/n15-1016","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1501.02598","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1501.02598","pdf_url":"https://arxiv.org/pdf/1501.02598","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":"","raw_type":"text"},{"id":"mag:1486723856","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1501.02598","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":"doi:10.48550/arxiv.1501.02598","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1501.02598","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/n15-1016","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/n15-1016","pdf_url":"https://doi.org/10.3115/v1/n15-1016","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W36903255","https://openalex.org/W155596317","https://openalex.org/W1507509966","https://openalex.org/W1527575280","https://openalex.org/W1662133657","https://openalex.org/W1958547877","https://openalex.org/W1968060331","https://openalex.org/W2009942101","https://openalex.org/W2014009760","https://openalex.org/W2098411764","https://openalex.org/W2102765684","https://openalex.org/W2110485445","https://openalex.org/W2112184938","https://openalex.org/W2117352571","https://openalex.org/W2120526973","https://openalex.org/W2123024445","https://openalex.org/W2131846894","https://openalex.org/W2137735870","https://openalex.org/W2141282920","https://openalex.org/W2141599568","https://openalex.org/W2145056192","https://openalex.org/W2149557440","https://openalex.org/W2159243025","https://openalex.org/W2161381512","https://openalex.org/W2171361956","https://openalex.org/W2250742840","https://openalex.org/W2251803266","https://openalex.org/W2252238675","https://openalex.org/W2311386336","https://openalex.org/W2950094539","https://openalex.org/W2950133940","https://openalex.org/W2950276680","https://openalex.org/W2951683451","https://openalex.org/W2953276893","https://openalex.org/W3110909889"],"related_works":["https://openalex.org/W2963871344","https://openalex.org/W2950133940","https://openalex.org/W2950577311","https://openalex.org/W2250742840","https://openalex.org/W2120526973","https://openalex.org/W1527575280","https://openalex.org/W2112184938","https://openalex.org/W2108598243","https://openalex.org/W2145056192","https://openalex.org/W1905882502","https://openalex.org/W1861492603","https://openalex.org/W2882319491","https://openalex.org/W2250676463","https://openalex.org/W2250539671","https://openalex.org/W2194775991","https://openalex.org/W2149557440","https://openalex.org/W2064675550","https://openalex.org/W2117539524","https://openalex.org/W1895577753","https://openalex.org/W1854884267"],"abstract_inverted_index":{"We":[0],"extend":[1],"the":[2,42,51,98,102,112,123],"SKIP-GRAM":[3],"model":[4,109],"of":[5,40,50,76,119,128,131],"Mikolov":[6],"et":[7],"al.":[8],"(2013a)":[9],"by":[10,26],"taking":[11],"visual":[12,48,64,83,117],"information":[13,84],"into":[14],"account.":[15],"Like":[16],"SKIP-GRAM,":[17],"our":[18],"multimodal":[19],"models":[20,43,69,114],"(MMSKIP-GRAM)":[21],"build":[22],"vector-based":[23],"word":[24],"representations":[25,49],"learning":[27],"to":[28,47,85,91,125],"predict":[29,61],"linguistic":[30,62],"contexts":[31],"in":[32,97],"text":[33],"corpora.":[34],"However,":[35],"for":[36],"a":[37,74],"restricted":[38],"set":[39],"words,":[41,87,121],"are":[44,105],"also":[45],"exposed":[46],"objects":[52],"they":[53,81],"denote":[54],"(extracted":[55],"from":[56],"natural":[57],"images),":[58],"and":[59,63,95],"must":[60],"features":[65],"jointly.":[66],"The":[67],"MMSKIP-GRAM":[68,113],"achieve":[70],"good":[71],"performance":[72],"on":[73],"variety":[75],"semantic":[77],"benchmarks.":[78],"Moreover,":[79],"since":[80],"propagate":[82],"all":[86],"we":[88],"use":[89],"them":[90],"improve":[92],"image":[93],"labeling":[94],"retrieval":[96],"zero-shot":[99],"setup,":[100],"where":[101],"test":[103],"concepts":[104],"never":[106],"seen":[107],"during":[108],"training.":[110],"Finally,":[111],"discover":[115],"intriguing":[116],"properties":[118],"abstract":[120],"paving":[122],"way":[124],"realistic":[126],"implementations":[127],"embodied":[129],"theories":[130],"meaning.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}