{"id":"https://openalex.org/W2799082722","doi":"https://doi.org/10.18653/v1/p18-1165","title":"Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning","display_name":"Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2799082722","doi":"https://doi.org/10.18653/v1/p18-1165","mag":"2799082722"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1165","pdf_url":"https://www.aclweb.org/anthology/P18-1165.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1165.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048307591","display_name":"Julia Kreutzer","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Julia Kreutzer","raw_affiliation_strings":["Computational Linguistics &","Heidelberg University, Heidelberg, Germany"],"affiliations":[{"raw_affiliation_string":"Computational Linguistics &","institution_ids":[]},{"raw_affiliation_string":"Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043618214","display_name":"Joshua Uyheng","orcid":"https://orcid.org/0000-0002-1631-6566"},"institutions":[{"id":"https://openalex.org/I19722","display_name":"Ateneo de Manila University","ror":"https://ror.org/053kevk63","country_code":"PH","type":"education","lineage":["https://openalex.org/I19722"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Joshua Uyheng","raw_affiliation_strings":["Departments of Psychology & Mathematics, Ateneo de Manila University, Philippines","Ateneo de Manila University, Quezon City, Philippines"],"affiliations":[{"raw_affiliation_string":"Departments of Psychology & Mathematics, Ateneo de Manila University, Philippines","institution_ids":["https://openalex.org/I19722"]},{"raw_affiliation_string":"Ateneo de Manila University, Quezon City, Philippines","institution_ids":["https://openalex.org/I19722"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011749347","display_name":"Stefan Riezler","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Riezler","raw_affiliation_strings":["Computational Linguistics &","IWR, Heidelberg University, Germany","Heidelberg University, Heidelberg, Germany"],"affiliations":[{"raw_affiliation_string":"Computational Linguistics &","institution_ids":[]},{"raw_affiliation_string":"IWR, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048307591"],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":0.8461,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79907477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1777","last_page":"1788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9851999878883362,"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/learnability","display_name":"Learnability","score":0.7819828391075134},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7220719456672668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6672097444534302},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6440036296844482},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5983399152755737},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5582611560821533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.542275071144104},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5354884266853333},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5171055793762207},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5108723044395447},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4254250228404999},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20853617787361145},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1928626298904419},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09674450755119324}],"concepts":[{"id":"https://openalex.org/C2777723229","wikidata":"https://www.wikidata.org/wiki/Q4367921","display_name":"Learnability","level":2,"score":0.7819828391075134},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7220719456672668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6672097444534302},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6440036296844482},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5983399152755737},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5582611560821533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.542275071144104},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5354884266853333},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5171055793762207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5108723044395447},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4254250228404999},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20853617787361145},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1928626298904419},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09674450755119324},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"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":6,"locations":[{"id":"doi:10.18653/v1/p18-1165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1165","pdf_url":"https://www.aclweb.org/anthology/P18-1165.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.10627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.10627","pdf_url":"https://arxiv.org/pdf/1805.10627","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2799082722","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1805.10627.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1805.10627","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.10627","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.60692/00crp-2xd10","is_oa":true,"landing_page_url":"https://doi.org/10.60692/00crp-2xd10","pdf_url":null,"source":{"id":"https://openalex.org/S7407051682","display_name":"Greater South Information System","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.60692/7z0zw-tyd07","is_oa":true,"landing_page_url":"https://doi.org/10.60692/7z0zw-tyd07","pdf_url":null,"source":{"id":"https://openalex.org/S7407051682","display_name":"Greater South Information System","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1165","pdf_url":"https://www.aclweb.org/anthology/P18-1165.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2799082722.pdf","grobid_xml":"https://content.openalex.org/works/W2799082722.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W27434444","https://openalex.org/W1514587017","https://openalex.org/W1539975474","https://openalex.org/W1600046456","https://openalex.org/W1614298861","https://openalex.org/W1771410628","https://openalex.org/W1815076433","https://openalex.org/W1832693441","https://openalex.org/W2016522586","https://openalex.org/W2064675550","https://openalex.org/W2089181240","https://openalex.org/W2095705004","https://openalex.org/W2098584016","https://openalex.org/W2101105183","https://openalex.org/W2130801532","https://openalex.org/W2144600658","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2156869222","https://openalex.org/W2188353343","https://openalex.org/W2250342921","https://openalex.org/W2251171258","https://openalex.org/W2251367463","https://openalex.org/W2257979135","https://openalex.org/W2513592723","https://openalex.org/W2546950329","https://openalex.org/W2567571499","https://openalex.org/W2580300496","https://openalex.org/W2606134370","https://openalex.org/W2621975677","https://openalex.org/W2757980860","https://openalex.org/W2950382198","https://openalex.org/W2962784628","https://openalex.org/W2962955856","https://openalex.org/W2963053969","https://openalex.org/W2963163972","https://openalex.org/W2963218093","https://openalex.org/W2963463964","https://openalex.org/W2963768805","https://openalex.org/W2964033619","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2964123521","https://openalex.org/W2964263543","https://openalex.org/W2964268978","https://openalex.org/W2964308564","https://openalex.org/W2964352247","https://openalex.org/W3003252051","https://openalex.org/W3204406378"],"related_works":["https://openalex.org/W2962897543","https://openalex.org/W2964123521","https://openalex.org/W2757930439","https://openalex.org/W3087946938","https://openalex.org/W2786930135","https://openalex.org/W2972500268","https://openalex.org/W3037924899","https://openalex.org/W2605369401","https://openalex.org/W208428353","https://openalex.org/W3177009489","https://openalex.org/W3104994094","https://openalex.org/W3091550845","https://openalex.org/W3212159807","https://openalex.org/W2435367904","https://openalex.org/W2966067376","https://openalex.org/W3167755691","https://openalex.org/W343811141","https://openalex.org/W2028357975","https://openalex.org/W2787188308","https://openalex.org/W3174426278"],"abstract_inverted_index":{"We":[0,25],"present":[1],"a":[2,43,109,141],"study":[3],"on":[4,39,55,114],"reinforcement":[5],"learning":[6],"(RL)":[7],"from":[8,131],"human":[9,30,137],"bandit":[10,20,31],"feedback":[11,70,89,116],"for":[12,83,117,122,144],"sequence-to-sequence":[13],"learning,":[14],"exemplified":[15],"by":[16,107],"the":[17,27,35,40,47,50,56],"task":[18],"of":[19,29,37,42,49,52,62,100,134],"neural":[21],"machine":[22],"translation":[23],"(NMT).":[24],"investigate":[26],"reliability":[28,38,80],"feedback,":[32,86,138],"and":[33,46,66,87,95],"analyze":[34],"influence":[36],"learnability":[41],"reward":[44,53,111],"estimator,":[45],"effect":[48],"quality":[51],"estimates":[54],"overall":[57],"RL":[58,121,127],"task.":[59],"Our":[60],"analysis":[61],"cardinal":[63,85,88,115],"(5-point":[64],"ratings)":[65],"ordinal":[67],"(pairwise":[68],"preferences)":[69],"shows":[71,125],"that":[72,126],"their":[73],"intra-and":[74],"inter-annotator":[75],"agreement":[76],"is":[77,81,90,128],"comparable.":[78],"Best":[79],"obtained":[82,106],"standardized":[84],"also":[91],"easiest":[92],"to":[93,140],"learn":[94],"generalize":[96],"from.":[97],"Finally,":[98],"improvements":[99],"over":[101],"1":[102],"BLEU":[103],"can":[104],"be":[105],"integrating":[108],"regressionbased":[110],"estimator":[112],"trained":[113],"800":[118],"translations":[119],"into":[120],"NMT.":[123],"This":[124],"possible":[129],"even":[130],"small":[132],"amounts":[133],"fairly":[135],"reliable":[136],"pointing":[139],"great":[142],"potential":[143],"applications":[145],"at":[146],"larger":[147],"scale.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}