{"id":"https://openalex.org/W2798299685","doi":"https://doi.org/10.18653/v1/p18-1169","title":"Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback","display_name":"Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798299685","doi":"https://doi.org/10.18653/v1/p18-1169","mag":"2798299685"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1169","pdf_url":"https://www.aclweb.org/anthology/P18-1169.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/P18-1169.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070442264","display_name":"Carolin Lawrence","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":"Carolin Lawrence","raw_affiliation_strings":["Heidelberg University, Heidelberg, Germany"],"affiliations":[{"raw_affiliation_string":"Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]},{"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":["Heidelberg University, Heidelberg, Germany"],"affiliations":[{"raw_affiliation_string":"Heidelberg University, Heidelberg, Germany","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070442264"],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":1.5443,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8447983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1820","last_page":"1830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9988999962806702,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983999729156494,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9467800855636597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8322903513908386},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6658762097358704},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6088755130767822},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5079901814460754},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.46138933300971985},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.44946908950805664},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32930266857147217},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06459066271781921}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9467800855636597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8322903513908386},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6658762097358704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6088755130767822},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5079901814460754},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.46138933300971985},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.44946908950805664},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32930266857147217},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06459066271781921},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/p18-1169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1169","pdf_url":"https://www.aclweb.org/anthology/P18-1169.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:1805.01252","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.01252","pdf_url":"https://arxiv.org/pdf/1805.01252","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:2798299685","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1805.01252","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.1805.01252","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.01252","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"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1169","pdf_url":"https://www.aclweb.org/anthology/P18-1169.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":[{"id":"https://openalex.org/G5398132153","display_name":null,"funder_award_id":"DFG grant","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"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/W2798299685.pdf","grobid_xml":"https://content.openalex.org/works/W2798299685.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1514587017","https://openalex.org/W1809653203","https://openalex.org/W1835900096","https://openalex.org/W1924770834","https://openalex.org/W2023286866","https://openalex.org/W2122124659","https://openalex.org/W2150291618","https://openalex.org/W2188353343","https://openalex.org/W2189089430","https://openalex.org/W2224454470","https://openalex.org/W2466325641","https://openalex.org/W2511149293","https://openalex.org/W2546950329","https://openalex.org/W2578341774","https://openalex.org/W2594229957","https://openalex.org/W2611818442","https://openalex.org/W2757344526","https://openalex.org/W2768398531","https://openalex.org/W2941519458","https://openalex.org/W2949800357","https://openalex.org/W2949888546","https://openalex.org/W2963655793","https://openalex.org/W2964033619","https://openalex.org/W2964308564","https://openalex.org/W2989631226"],"related_works":["https://openalex.org/W2963393617","https://openalex.org/W3199724653","https://openalex.org/W3111500217","https://openalex.org/W3098502857","https://openalex.org/W3101314357","https://openalex.org/W2990413070","https://openalex.org/W2396229782","https://openalex.org/W3092995464","https://openalex.org/W2998219625","https://openalex.org/W1570672595","https://openalex.org/W191985209","https://openalex.org/W3092068599","https://openalex.org/W2889990052","https://openalex.org/W2988536330","https://openalex.org/W2609776793","https://openalex.org/W3131701661","https://openalex.org/W3122606629","https://openalex.org/W2476698163","https://openalex.org/W2969585892","https://openalex.org/W3166204731"],"abstract_inverted_index":{"Counterfactual":[0],"learning":[1,36,45],"from":[2],"human":[3],"bandit":[4],"feedback":[5,11],"describes":[6],"a":[7,18,27,43,52],"scenario":[8],"where":[9],"user":[10],"on":[12],"the":[13,47,56],"quality":[14],"of":[15,17,55],"outputs":[16],"historic":[19],"system":[20],"is":[21],"logged":[22],"and":[23],"used":[24],"to":[25,33,38,60,71],"improve":[26],"target":[28],"system.":[29],"We":[30],"show":[31],"how":[32],"apply":[34],"this":[35],"framework":[37],"neural":[39],"semantic":[40],"parsing.":[41],"From":[42],"machine":[44],"perspective,":[46],"key":[48],"challenge":[49],"lies":[50],"in":[51,64],"proper":[53],"reweighting":[54],"estimator":[57],"so":[58],"as":[59],"avoid":[61],"known":[62],"degeneracies":[63],"counterfactual":[65],"learning,":[66],"while":[67],"still":[68],"being":[69],"applicable":[70],"stochastic":[72],"gradient":[73],"optimization.":[74]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}