{"id":"https://openalex.org/W2599940792","doi":"https://doi.org/10.24963/ijcai.2017/385","title":"End-to-end optimization of goal-driven and visually grounded dialogue systems","display_name":"End-to-end optimization of goal-driven and visually grounded dialogue systems","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2599940792","doi":"https://doi.org/10.24963/ijcai.2017/385","mag":"2599940792"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/385","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/385","pdf_url":"https://www.ijcai.org/proceedings/2017/0385.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0385.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024394972","display_name":"Florian Strub","orcid":"https://orcid.org/0000-0001-7271-5345"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4387153239","display_name":"Centre de Recherche en Informatique, Signal et Automatique de Lille","ror":"https://ror.org/05vrs3189","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]},{"id":"https://openalex.org/I7454413","display_name":"\u00c9cole Centrale de Lille","ror":"https://ror.org/01x441g73","country_code":"FR","type":"education","lineage":["https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Florian Strub","raw_affiliation_strings":["University of Lille, Inria, UMR 9189 - CRIStAL","Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 -CRIStAL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lille, Inria, UMR 9189 - CRIStAL","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4387153239"]},{"raw_affiliation_string":"Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 -CRIStAL","institution_ids":["https://openalex.org/I4387153239","https://openalex.org/I7454413"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103854790","display_name":"Harm de Vries","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":"Harm de Vries","raw_affiliation_strings":["University of Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Montreal","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113360576","display_name":"J\u00e9r\u00e9mie Mary","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4387153239","display_name":"Centre de Recherche en Informatique, Signal et Automatique de Lille","ror":"https://ror.org/05vrs3189","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2279609970","https://openalex.org/I4387153239","https://openalex.org/I7454413"]},{"id":"https://openalex.org/I7454413","display_name":"\u00c9cole Centrale de Lille","ror":"https://ror.org/01x441g73","country_code":"FR","type":"education","lineage":["https://openalex.org/I7454413"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J\u00e9r\u00e9mie Mary","raw_affiliation_strings":["University of Lille, Inria, UMR 9189 - CRIStAL","Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 -CRIStAL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Lille, Inria, UMR 9189 - CRIStAL","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4387153239"]},{"raw_affiliation_string":"Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 -CRIStAL","institution_ids":["https://openalex.org/I4387153239","https://openalex.org/I7454413"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103033215","display_name":"Bilal Piot","orcid":"https://orcid.org/0000-0003-3906-950X"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bilal Piot","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112608251","display_name":"Aaron Courville","orcid":"https://orcid.org/0000-0001-6223-0301"},"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":"Aaron Courville","raw_affiliation_strings":["University of Montreal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Montreal","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065100569","display_name":"Olivier Pietquin","orcid":"https://orcid.org/0000-0002-5386-465X"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5373,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.96705236,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2765","last_page":"2771"},"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/T12031","display_name":"Speech and dialogue systems","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":0.9987999796867371,"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":0.7920964956283569},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7204545140266418},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6456819176673889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6346328854560852},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5855574011802673},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5105117559432983},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4989438056945801},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4720733165740967},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07727682590484619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7920964956283569},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7204545140266418},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6456819176673889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6346328854560852},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5855574011802673},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5105117559432983},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4989438056945801},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4720733165740967},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07727682590484619},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/385","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/385","pdf_url":"https://www.ijcai.org/proceedings/2017/0385.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2017/385","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/385","pdf_url":"https://www.ijcai.org/proceedings/2017/0385.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1729111207","display_name":"Extraction and Transfer of Knowledge in Reinforcement Learning","funder_award_id":"ANR-14-CE24-0010","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8294442158","display_name":null,"funder_award_id":"2015-2020","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"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/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2599940792.pdf","grobid_xml":"https://content.openalex.org/works/W2599940792.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1518951372","https://openalex.org/W1591706642","https://openalex.org/W1757949796","https://openalex.org/W1777239053","https://openalex.org/W1861492603","https://openalex.org/W2040123554","https://openalex.org/W2095908550","https://openalex.org/W2106547558","https://openalex.org/W2109038907","https://openalex.org/W2117989772","https://openalex.org/W2140679639","https://openalex.org/W2155027007","https://openalex.org/W2156050092","https://openalex.org/W2163068732","https://openalex.org/W2168490009","https://openalex.org/W2176263492","https://openalex.org/W2257979135","https://openalex.org/W2438667436","https://openalex.org/W2463565445","https://openalex.org/W2558533273","https://openalex.org/W2558809543","https://openalex.org/W2563399268","https://openalex.org/W2603266952","https://openalex.org/W2950483141","https://openalex.org/W2962854379","https://openalex.org/W2963903950","https://openalex.org/W2964352247","https://openalex.org/W4230563027","https://openalex.org/W4232378919","https://openalex.org/W4297809080","https://openalex.org/W4300489070"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2732813147","https://openalex.org/W2143460112","https://openalex.org/W2042906257"],"abstract_inverted_index":{"End-to-end":[0],"design":[1],"of":[2,42,49,120,127],"dialogue":[3,29,64],"systems":[4],"has":[5],"recently":[6],"become":[7],"a":[8,32,43,78,129,133],"popular":[9],"research":[10],"topic":[11],"thanks":[12],"to":[13,56,63,83],"powerful":[14],"tools":[15],"such":[16],"as":[17,31,65,67],"encoder-decoder":[18],"architectures":[19],"for":[20],"sequence-to-sequence":[21],"learning.":[22],"Yet,":[23],"most":[24],"current":[25],"approaches":[26],"cast":[27],"human-machine":[28],"management":[30],"supervised":[33],"learning":[34],"problem,":[35],"aiming":[36],"at":[37,115],"predicting":[38],"the":[39,46,50,59,91,100,105,118,125],"next":[40],"utterance":[41],"participant":[44],"given":[45],"full":[47],"history":[48],"dialogue.":[51],"This":[52,95],"vision":[53],"may":[54],"fail":[55],"correctly":[57],"render":[58],"planning":[60],"problem":[61,119],"inherent":[62],"well":[66],"its":[68],"contextual":[69],"and":[70,111,124],"grounded":[71,86],"nature.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"introduce":[77],"Deep":[79],"Reinforcement":[80],"Learning":[81],"method":[82],"optimize":[84],"visually":[85],"task-oriented":[87],"dialogues,":[88],"based":[89],"on":[90,99],"policy":[92],"gradient":[93],"algorithm.":[94],"approach":[96],"is":[97],"tested":[98],"question":[101],"generation":[102],"task":[103,126],"from":[104],"dataset":[106],"GuessWhat?!":[107],"containing":[108],"120k":[109],"dialogues":[110,123],"provides":[112],"encouraging":[113],"results":[114],"solving":[116],"both":[117],"generating":[121],"natural":[122],"discovering":[128],"specific":[130],"object":[131],"in":[132],"complex":[134],"picture.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}