{"id":"https://openalex.org/W2795571593","doi":"https://doi.org/10.1145/3173574.3173851","title":"Emotional Dialogue Generation using Image-Grounded Language Models","display_name":"Emotional Dialogue Generation using Image-Grounded Language Models","publication_year":2018,"publication_date":"2018-04-20","ids":{"openalex":"https://openalex.org/W2795571593","doi":"https://doi.org/10.1145/3173574.3173851","mag":"2795571593"},"language":"en","primary_location":{"id":"doi:10.1145/3173574.3173851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3173574.3173851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5069079602","display_name":"Bernd Huber","orcid":"https://orcid.org/0000-0002-9176-2208"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bernd Huber","raw_affiliation_strings":["Harvard University & Microsoft Research, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University & Microsoft Research, Boston, MA, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681741","display_name":"Daniel McDuff","orcid":"https://orcid.org/0000-0001-7313-0082"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel McDuff","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015656536","display_name":"Chris Brockett","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Brockett","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107838508","display_name":"Michel Galley","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michel Galley","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057693146","display_name":"Bill Dolan","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bill Dolan","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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/T12031","display_name":"Speech and dialogue systems","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.788127601146698},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6639977693557739},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.611194372177124},{"id":"https://openalex.org/keywords/facial-expression","display_name":"Facial expression","score":0.5379899144172668},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5202164053916931},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5132389068603516},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49839043617248535},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49008095264434814},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4692639708518982},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4261187016963959},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4192578196525574},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.4101424515247345},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12026715278625488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.788127601146698},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6639977693557739},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.611194372177124},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.5379899144172668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5202164053916931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5132389068603516},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49839043617248535},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49008095264434814},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4692639708518982},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4261187016963959},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4192578196525574},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4101424515247345},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12026715278625488},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3173574.3173851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3173574.3173851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W10957333","https://openalex.org/W136732505","https://openalex.org/W613277099","https://openalex.org/W1518951372","https://openalex.org/W1588539311","https://openalex.org/W1589781773","https://openalex.org/W1591706642","https://openalex.org/W1614298861","https://openalex.org/W1889777305","https://openalex.org/W1933349210","https://openalex.org/W1985945240","https://openalex.org/W2031738304","https://openalex.org/W2060833990","https://openalex.org/W2101105183","https://openalex.org/W2101623580","https://openalex.org/W2109636054","https://openalex.org/W2134670479","https://openalex.org/W2135556254","https://openalex.org/W2136058926","https://openalex.org/W2140054881","https://openalex.org/W2151814822","https://openalex.org/W2157025439","https://openalex.org/W2229710742","https://openalex.org/W2250539671","https://openalex.org/W2250745056","https://openalex.org/W2294699749","https://openalex.org/W2299275441","https://openalex.org/W2302086703","https://openalex.org/W2395639500","https://openalex.org/W2405187948","https://openalex.org/W2406390611","https://openalex.org/W2525450952","https://openalex.org/W2561029672","https://openalex.org/W2583186419","https://openalex.org/W2591734415","https://openalex.org/W2608438166","https://openalex.org/W2613278928","https://openalex.org/W2741321799","https://openalex.org/W2768661419","https://openalex.org/W2919115771","https://openalex.org/W2949888546","https://openalex.org/W2962883855","https://openalex.org/W2963062932","https://openalex.org/W2963206148","https://openalex.org/W2963351776","https://openalex.org/W2963903950","https://openalex.org/W2963963856","https://openalex.org/W3105184045","https://openalex.org/W4285719527","https://openalex.org/W4297823417","https://openalex.org/W4302315070"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1977056376","https://openalex.org/W1990545028","https://openalex.org/W4312622923","https://openalex.org/W2728430307","https://openalex.org/W2169518243","https://openalex.org/W2107786128","https://openalex.org/W2123478443","https://openalex.org/W2048368023","https://openalex.org/W2735469505"],"abstract_inverted_index":{"Computer-based":[0],"conversational":[1,55],"agents":[2],"are":[3],"becoming":[4],"ubiquitous.":[5],"However,":[6],"for":[7,81],"these":[8],"systems":[9],"to":[10,15,22,27,44,106],"be":[11,20,75,119],"engaging":[12],"and":[13,62,92,111,114],"valuable":[14],"the":[16,49,71,78,83,115,123,131],"user,":[17],"they":[18],"must":[19],"able":[21],"express":[23],"emotion,":[24],"in":[25],"addition":[26],"providing":[28,45],"informative":[29],"responses.":[30],"Humans":[31],"rely":[32],"on":[33,89,122,139],"much":[34],"more":[35,108],"than":[36],"language":[37,142],"during":[38],"conversations;":[39],"visual":[40,58],"information":[41],"is":[42],"key":[43,68],"context.":[46],"We":[47,65,85],"present":[48],"first":[50],"example":[51],"of":[52,70,97,134],"an":[53],"image-grounded":[54],"agent":[56],"using":[57],"sentiment,":[59],"facial":[60],"expression":[61],"scene":[63],"features.":[64],"show":[66],"that":[67],"qualities":[69,117],"generated":[72],"dialogue":[73,135],"can":[74,118],"manipulated":[76],"by":[77],"features":[79,125],"used":[80],"training":[82],"agent.":[84],"evaluate":[86],"our":[87,128],"model":[88,129],"a":[90],"large":[91],"very":[93],"challenging":[94],"real-world":[95],"dataset":[96],"conversations":[98],"from":[99],"social":[100],"media":[101],"(Twitter).":[102],"The":[103],"image-grounding":[104],"leads":[105],"significantly":[107],"informative,":[109],"emotional":[110],"specific":[112],"responses,":[113],"exact":[116],"tuned":[120],"depending":[121],"image":[124],"used.":[126],"Furthermore,":[127],"improves":[130],"objective":[132],"quality":[133],"responses":[136],"when":[137],"evaluated":[138],"standard":[140],"natural":[141],"metrics.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}