{"id":"https://openalex.org/W2963712524","doi":"https://doi.org/10.1609/aaai.v33i01.33016722","title":"Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning","display_name":"Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963712524","doi":"https://doi.org/10.1609/aaai.v33i01.33016722","mag":"2963712524"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33016722","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016722","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4644/4522","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4644/4522","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101651748","display_name":"Ziming Li","orcid":"https://orcid.org/0009-0004-7529-7176"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Ziming Li","raw_affiliation_strings":["University of Amsterdam"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026947055","display_name":"Julia Kiseleva","orcid":"https://orcid.org/0000-0002-3789-9588"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Julia Kiseleva","raw_affiliation_strings":["University of Amsterdam"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031439294","display_name":"Maarten de Rijke","orcid":"https://orcid.org/0000-0002-1086-0202"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maarten De Rijke","raw_affiliation_strings":["University of Amsterdam"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101651748"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":5.1873,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.95728516,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"33","issue":"01","first_page":"6722","last_page":"6729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9904000163078308,"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":0.9732000231742859,"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/discriminator","display_name":"Discriminator","score":0.8557183742523193},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7651660442352295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7619774341583252},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7265819311141968},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.669792890548706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6490013599395752},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5682110786437988},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5298136472702026},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.47551852464675903},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46623513102531433},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07606565952301025},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.0752178430557251}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8557183742523193},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7651660442352295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619774341583252},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7265819311141968},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.669792890548706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6490013599395752},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5682110786437988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5298136472702026},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.47551852464675903},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46623513102531433},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07606565952301025},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0752178430557251},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v33i01.33016722","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016722","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4644/4522","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:dare.uva.nl:publications/d60b9c16-b8cd-4828-9b94-ef52dcdc3e73","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/dialogue-generation-from-imitation-learning-to-inverse-reinforcement-learning(d60b9c16-b8cd-4828-9b94-ef52dcdc3e73).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, Z, Kiseleva, J & de Rijke, M 2019, Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning. in Thirty-Third AAAI Conference on Artificial Intelligence, Thirty-First Conference on Innovative Applications of Artificial Intelligence, The Ninth Symposium on Educational Advances in Artificial Intelligence : AAAI-19, IAAI-19, EAAI-20 : January 27-February 1, 2019, Hilton Hawaiian Village, Honolulu, Hawaii, USA. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, Palo Alto, California, pp. 6722-6729, 33rd AAAI Conference on Artificial Intelligence, Honolulu, Hawaii, United States, 27/01/19. https://doi.org/10.1609/aaai.v33i01.33016722","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/d60b9c16-b8cd-4828-9b94-ef52dcdc3e73","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/dialogue-generation-from-imitation-learning-to-inverse-reinforcement-learning(d60b9c16-b8cd-4828-9b94-ef52dcdc3e73).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Thirty-Third AAAI Conference on Artificial Intelligence, Thirty-First Conference on Innovative Applications of Artificial Intelligence, The Ninth Symposium on Educational Advances in Artificial Intelligence: AAAI-19, IAAI-19, EAAI-20 : January 27-February 1, 2019, Hilton Hawaiian Village, Honolulu, Hawaii, USA, 6722 - 6729","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33016722","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33016722","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4644/4522","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G8589651859","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963712524.pdf","grobid_xml":"https://content.openalex.org/works/W2963712524.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1518951372","https://openalex.org/W1522301498","https://openalex.org/W1654173042","https://openalex.org/W1958706068","https://openalex.org/W2098774185","https://openalex.org/W2133012565","https://openalex.org/W2147544021","https://openalex.org/W2159640018","https://openalex.org/W2250645967","https://openalex.org/W2250895046","https://openalex.org/W2290104316","https://openalex.org/W2328886022","https://openalex.org/W2399880602","https://openalex.org/W2521114121","https://openalex.org/W2581637843","https://openalex.org/W2798838035","https://openalex.org/W2962883855","https://openalex.org/W2963167310","https://openalex.org/W2963277051","https://openalex.org/W2963508354","https://openalex.org/W2963903950","https://openalex.org/W2963963856","https://openalex.org/W3022187094","https://openalex.org/W6636805335","https://openalex.org/W6714618025","https://openalex.org/W6718092244","https://openalex.org/W6727329663","https://openalex.org/W6732564789"],"related_works":["https://openalex.org/W2995777218","https://openalex.org/W2953246223","https://openalex.org/W4293320219","https://openalex.org/W4283584549","https://openalex.org/W3110074278","https://openalex.org/W2618858825","https://openalex.org/W2554314924","https://openalex.org/W2998859928","https://openalex.org/W3151498616","https://openalex.org/W4381885966"],"abstract_inverted_index":{"The":[0,19],"performance":[1,103,134],"of":[2,11,73,104],"adversarial":[3,59,65,74],"dialogue":[4,60,85],"generation":[5,61,86],"models":[6],"relies":[7],"on":[8],"the":[9,12,17,35,50,71,102,105,136],"quality":[10],"reward":[13,20,82,95],"signal":[14,21,96],"produced":[15],"by":[16],"discriminator.":[18],"from":[22],"a":[23,40,56,80,90],"poor":[24],"discriminator":[25],"can":[26,88,125],"be":[27],"very":[28],"sparse":[29],"and":[30,93,111,130],"unstable,":[31],"which":[32],"may":[33],"lead":[34],"generator":[36,98],"to":[37,44,63],"fall":[38],"into":[39],"local":[41],"optimum":[42],"or":[43],"produce":[45],"nonsense":[46],"replies.":[47],"To":[48],"alleviate":[49],"first":[51,54],"problem,":[52],"we":[53,78],"extend":[55],"recently":[57],"proposed":[58],"method":[62],"an":[64],"imitation":[66],"learning":[67],"solution.":[68],"Then,":[69],"in":[70,114],"framework":[72],"inverse":[75],"reinforcement":[76],"learning,":[77],"propose":[79],"new":[81],"model":[83,107,124],"for":[84,97],"that":[87,122],"provide":[89],"more":[91,127],"accurate":[92],"precise":[94],"training.":[99],"We":[100],"evaluate":[101],"resulting":[106],"with":[108],"automatic":[109],"metrics":[110],"human":[112],"evaluations":[113],"two":[115],"annotation":[116],"settings.":[117],"Our":[118],"experimental":[119],"results":[120],"demonstrate":[121],"our":[123],"generate":[126],"high-quality":[128],"responses":[129],"achieve":[131],"higher":[132],"overall":[133],"than":[135],"state-of-the-art.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":8}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}