{"id":"https://openalex.org/W2963730239","doi":"https://doi.org/10.24963/ijcai.2018/606","title":"Toward Diverse Text Generation with Inverse Reinforcement Learning","display_name":"Toward Diverse Text Generation with Inverse Reinforcement Learning","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2963730239","doi":"https://doi.org/10.24963/ijcai.2018/606","mag":"2963730239"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/606","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/606","pdf_url":"https://www.ijcai.org/proceedings/2018/0606.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh 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/2018/0606.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101989380","display_name":"Zhan Shi","orcid":"https://orcid.org/0000-0001-6854-4686"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Shi","raw_affiliation_strings":["School of Computer Science, Fudan University","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028108458","display_name":"Xinchi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinchi Chen","raw_affiliation_strings":["School of Computer Science, Fudan University","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044665993","display_name":"Xipeng Qiu","orcid":"https://orcid.org/0000-0001-7163-5247"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xipeng Qiu","raw_affiliation_strings":["School of Computer Science, Fudan University","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088834359","display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":["School of Computer Science, Fudan University","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Intelligent Information Processing, Fudan University School of Computer Science, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5044665993"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":5.6411,"has_fulltext":true,"cited_by_count":87,"citation_normalized_percentile":{"value":0.97027142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4361","last_page":"4367"},"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":0.984499990940094,"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":0.9833999872207642,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.77293461561203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7424424886703491},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7088207602500916},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6726753115653992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6378539800643921},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5355308651924133},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48657524585723877},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.48190978169441223},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4732178747653961},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45199042558670044},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07936060428619385}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.77293461561203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7424424886703491},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7088207602500916},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6726753115653992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6378539800643921},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5355308651924133},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48657524585723877},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.48190978169441223},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4732178747653961},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45199042558670044},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07936060428619385},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/606","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/606","pdf_url":"https://www.ijcai.org/proceedings/2018/0606.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/606","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/606","pdf_url":"https://www.ijcai.org/proceedings/2018/0606.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3294370371","display_name":null,"funder_award_id":"2017YFB1002104","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3514936698","display_name":null,"funder_award_id":"No.2017YFB1002104","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4666185321","display_name":null,"funder_award_id":"16JC1420401","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G6449467950","display_name":null,"funder_award_id":"17JC1404100","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G6564481282","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u795e\u7ecf\u7f51\u7edc\u7684\u7aef\u5230\u7aef\u81ea\u52a8\u95ee\u7b54\u7cfb\u7edf\u7814\u7a76","funder_award_id":"61672162","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7475107363","display_name":null,"funder_award_id":"16JC1420401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963730239.pdf","grobid_xml":"https://content.openalex.org/works/W2963730239.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W592244745","https://openalex.org/W648786980","https://openalex.org/W1810943226","https://openalex.org/W1884859883","https://openalex.org/W1889081078","https://openalex.org/W2098774185","https://openalex.org/W2119717200","https://openalex.org/W2142972908","https://openalex.org/W2290104316","https://openalex.org/W2399880602","https://openalex.org/W2523469089","https://openalex.org/W2593383075","https://openalex.org/W2616969219","https://openalex.org/W2625357353","https://openalex.org/W2771099609","https://openalex.org/W2787188308","https://openalex.org/W2788714981","https://openalex.org/W2951507724","https://openalex.org/W2951824008","https://openalex.org/W2963131369","https://openalex.org/W2963248348","https://openalex.org/W2963373786","https://openalex.org/W2964268978","https://openalex.org/W3022187094","https://openalex.org/W4293320219","https://openalex.org/W4294294142","https://openalex.org/W4320013936","https://openalex.org/W6791858558","https://openalex.org/W6834709193","https://openalex.org/W6863994431","https://openalex.org/W6864014924"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W2970690932","https://openalex.org/W2110715801"],"abstract_inverted_index":{"Text":[0],"generation":[1,116],"is":[2],"a":[3,67],"crucial":[4],"task":[5],"in":[6,22,50,94],"NLP.":[7],"Recently,":[8],"several":[9],"adversarial":[10,87],"generative":[11],"models":[12,27],"have":[13],"been":[14],"proposed":[15,135],"to":[16,45,78,85,125],"improve":[17],"the":[18,35,63,80,86,89,105,115,143],"exposure":[19],"bias":[20],"problem":[21],"text":[23,60],"generation.":[24,61],"Though":[25],"these":[26,47],"gain":[28],"great":[29],"success,":[30],"they":[31],"still":[32],"suffer":[33],"from":[34],"problems":[36],"of":[37],"reward":[38,68,90,106,112],"sparsity":[39],"and":[40,73,91],"mode":[41],"collapse.":[42],"In":[43],"order":[44],"address":[46],"two":[48,102],"problems,":[49],"this":[51],"paper,":[52],"we":[53],"employ":[54],"inverse":[55],"reinforcement":[56],"learning":[57],"(IRL)":[58],"for":[59],"Specifically,":[62],"IRL":[64,95],"framework":[65],"learns":[66],"function":[69,93,107],"on":[70],"training":[71],"data,":[72],"then":[74],"an":[75],"optimal":[76],"policy":[77,92,122],"maximum":[79],"expected":[81],"total":[82],"reward.":[83],"Similar":[84],"models,":[88],"are":[96],"optimized":[97],"alternately.":[98],"Our":[99],"method":[100,136],"has":[101],"advantages:":[103],"(1)":[104],"can":[108,137],"produce":[109],"more":[110,127],"dense":[111],"signals.":[113],"(2)":[114],"policy,":[117],"trained":[118],"by":[119],"``entropy":[120],"regularized''":[121],"gradient,":[123],"encourages":[124],"generate":[126,138],"diversified":[128],"texts.":[129],"Experiment":[130],"results":[131],"demonstrate":[132],"that":[133],"our":[134],"higher":[139],"quality":[140],"texts":[141],"than":[142],"previous":[144],"methods.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}