{"id":"https://openalex.org/W2740707878","doi":"https://doi.org/10.24963/ijcai.2017/432","title":"Sequence Prediction with Unlabeled Data by Reward Function Learning","display_name":"Sequence Prediction with Unlabeled Data by Reward Function Learning","publication_year":2017,"publication_date":"2017-07-28","ids":{"openalex":"https://openalex.org/W2740707878","doi":"https://doi.org/10.24963/ijcai.2017/432","mag":"2740707878"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2017/432","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/432","pdf_url":"https://www.ijcai.org/proceedings/2017/0432.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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2017/0432.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102750692","display_name":"Lijun Wu","orcid":"https://orcid.org/0000-0002-3530-590X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lijun Wu","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032277491","display_name":"Zhao Li","orcid":"https://orcid.org/0000-0002-5056-0351"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034685928","display_name":"Jianhuang Lai","orcid":"https://orcid.org/0000-0003-3883-2024"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhuang Lai","raw_affiliation_strings":["Guangdong Key Laboratory of Information Security Technology","School of Data and Computer Science, Sun Yat-sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Information Security Technology","institution_ids":[]},{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115592065","display_name":"Tie\u2010Yan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102750692"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":2.2891,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.91004029,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3098","last_page":"3104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9908999800682068,"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":0.760951042175293},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7190068960189819},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.695972204208374},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6678080558776855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5955325365066528},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5215254426002502},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46891459822654724},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44723111391067505},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4454529881477356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760951042175293},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7190068960189819},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.695972204208374},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6678080558776855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5955325365066528},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5215254426002502},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46891459822654724},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44723111391067505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4454529881477356},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2017/432","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/432","pdf_url":"https://www.ijcai.org/proceedings/2017/0432.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.2017/432","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2017/432","pdf_url":"https://www.ijcai.org/proceedings/2017/0432.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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2740707878.pdf","grobid_xml":"https://content.openalex.org/works/W2740707878.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W2061562262","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2113021982","https://openalex.org/W2119717200","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2157331557","https://openalex.org/W2158349948","https://openalex.org/W2176263492","https://openalex.org/W2546938941","https://openalex.org/W2561274697","https://openalex.org/W2905927205","https://openalex.org/W2952729433","https://openalex.org/W2953830716","https://openalex.org/W2962965405","https://openalex.org/W2963216553","https://openalex.org/W2963463964","https://openalex.org/W2964308564","https://openalex.org/W2964352247","https://openalex.org/W3041866211","https://openalex.org/W4230563027","https://openalex.org/W4307459710"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W2973759123","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,147],"(RL),":[2],"which":[3,35],"has":[4],"been":[5],"successfully":[6],"applied":[7],"to":[8,17,32,42,53,58,74,80],"sequence":[9,31,72],"prediction,":[10],"introduces":[11],"\\textit{reward}":[12],"as":[13,93],"sequence-level":[14],"supervision":[15,143],"signal":[16],"evaluate":[18],"the":[19,29,37,82,90,108,137,146],"quality":[20],"of":[21,39],"a":[22,121],"generated":[23],"sequence.":[24],"Existing":[25],"RL":[26,40,69],"approaches":[27],"use":[28,89],"ground-truth":[30],"define":[33],"reward,":[34],"limits":[36],"application":[38],"techniques":[41],"labeled":[43,46,86],"data.":[44,62,77,151],"Since":[45],"data":[47,87,98,106,132],"is":[48,56],"usually":[49],"scarce":[50],"and/or":[51],"costly":[52],"collect,":[54],"it":[55],"desirable":[57],"leverage":[59],"large-scale":[60],"unlabeled":[61,76,97,105,117,150],"In":[63],"this":[64],"paper,":[65],"we":[66,101,119],"extend":[67],"existing":[68],"methods":[70],"for":[71,96],"prediction":[73],"exploit":[75],"We":[78,152],"propose":[79,120],"learn":[81,103],"reward":[83,92,115,123,139],"function":[84],"from":[85,104],"and":[88,144,161],"predicted":[91],"\\textit{pseudo":[94],"reward}":[95],"so":[99],"that":[100,136],"can":[102,140],"using":[107],"pseudo":[109,114,138],"reward.":[110],"To":[111],"get":[112],"good":[113,142],"on":[116,149,156],"data,":[118],"RNN-based":[122],"network":[124],"with":[125,129],"attention":[126],"mechanism,":[127],"trained":[128],"purposely":[130],"biased":[131],"distribution.":[133],"Experiments":[134],"show":[135],"provide":[141],"guide":[145],"process":[148],"observe":[153],"significant":[154],"improvements":[155],"both":[157],"neural":[158],"machine":[159],"translation":[160],"text":[162],"summarization.":[163]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}