{"id":"https://openalex.org/W2963696295","doi":"https://doi.org/10.18653/v1/d17-1063","title":"Learning how to Active Learn: A Deep Reinforcement Learning Approach","display_name":"Learning how to Active Learn: A Deep Reinforcement Learning Approach","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2963696295","doi":"https://doi.org/10.18653/v1/d17-1063","mag":"2963696295"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1063","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1063","pdf_url":"https://www.aclweb.org/anthology/D17-1063.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1063.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100400497","display_name":"Meng Fang","orcid":"https://orcid.org/0000-0003-0793-9187"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Fang","raw_affiliation_strings":["School of Computing and Information Systems The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems The University of Melbourne","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064837903","display_name":"Yuan Li","orcid":"https://orcid.org/0000-0001-9004-5146"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["School of Computing and Information Systems The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems The University of Melbourne","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078530959","display_name":"Trevor Cohn","orcid":"https://orcid.org/0000-0003-4363-1673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trevor Cohn","raw_affiliation_strings":["School of Computing and Information Systems The University of Melbourne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems The University of Melbourne","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.874,"has_fulltext":true,"cited_by_count":256,"citation_normalized_percentile":{"value":0.9904492,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"595","last_page":"605"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9998999834060669,"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":0.9962999820709229,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9932000041007996,"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":0.801217794418335},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7981741428375244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7020260095596313},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.6808727979660034},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6618714332580566},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6580143570899963},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5965166687965393},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5134385824203491},{"id":"https://openalex.org/keywords/cognitive-reframing","display_name":"Cognitive reframing","score":0.5103611350059509},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.494245320558548},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.47634032368659973},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.44850954413414},{"id":"https://openalex.org/keywords/instance-based-learning","display_name":"Instance-based learning","score":0.44695812463760376},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.44430315494537354},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.42117422819137573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.801217794418335},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7981741428375244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7020260095596313},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.6808727979660034},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6618714332580566},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6580143570899963},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5965166687965393},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5134385824203491},{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.5103611350059509},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.494245320558548},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.47634032368659973},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.44850954413414},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.44695812463760376},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.44430315494537354},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.42117422819137573},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d17-1063","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1063","pdf_url":"https://www.aclweb.org/anthology/D17-1063.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1063","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1063","pdf_url":"https://www.aclweb.org/anthology/D17-1063.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8016956108","display_name":null,"funder_award_id":"HR0011-15-C-0114","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963696295.pdf","grobid_xml":"https://content.openalex.org/works/W2963696295.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W142858861","https://openalex.org/W173861811","https://openalex.org/W834081922","https://openalex.org/W1484210532","https://openalex.org/W1514707997","https://openalex.org/W1658008008","https://openalex.org/W1832693441","https://openalex.org/W1947291763","https://openalex.org/W2080021732","https://openalex.org/W2085989833","https://openalex.org/W2114663556","https://openalex.org/W2116582594","https://openalex.org/W2144452292","https://openalex.org/W2145339207","https://openalex.org/W2147880316","https://openalex.org/W2155007355","https://openalex.org/W2168199177","https://openalex.org/W2171671120","https://openalex.org/W2173564293","https://openalex.org/W2251699420","https://openalex.org/W2257979135","https://openalex.org/W2270364989","https://openalex.org/W2295582178","https://openalex.org/W2310425190","https://openalex.org/W2426267443","https://openalex.org/W2463000881","https://openalex.org/W2522489477","https://openalex.org/W2616180702","https://openalex.org/W2903158431","https://openalex.org/W2951799221","https://openalex.org/W2951911250","https://openalex.org/W2962702662","https://openalex.org/W2962858248","https://openalex.org/W2963430173","https://openalex.org/W2964036520","https://openalex.org/W2964161785","https://openalex.org/W4285719527","https://openalex.org/W4298174377","https://openalex.org/W4319988532"],"related_works":["https://openalex.org/W2098239572","https://openalex.org/W184546935","https://openalex.org/W36398315","https://openalex.org/W4205569898","https://openalex.org/W1492505081","https://openalex.org/W1756896031","https://openalex.org/W3210156800","https://openalex.org/W4310801741","https://openalex.org/W2186368657","https://openalex.org/W2782796106"],"abstract_inverted_index":{"Active":[0],"learning":[1,61,65,69,83],"aims":[2],"to":[3,98,101],"select":[4],"a":[5,14,54,63,70],"small":[6],"subset":[7],"of":[8,34,43,80],"data":[9,19,71],"for":[10],"annotation":[11],"such":[12,35],"that":[13],"classifier":[15],"learned":[16,92],"on":[17,95],"the":[18,32,41,59,75,78,81,89],"is":[20,24,37],"highly":[21],"accurate.":[22],"This":[23],"usually":[25],"done":[26],"using":[27,93,108],"heuristic":[28],"selection":[29,72,90],"methods,":[30],"however":[31],"effectiveness":[33],"methods":[36],"limited":[38],"and":[39,67],"moreover,":[40],"performance":[42],"heuristics":[44],"varies":[45],"between":[46],"datasets.":[47],"To":[48],"address":[49],"these":[50],"shortcomings,":[51],"we":[52],"introduce":[53],"novel":[55],"formulation":[56],"by":[57],"reframing":[58],"active":[60,82,118],"as":[62],"reinforcement":[64],"problem":[66],"explicitly":[68],"policy,":[73],"where":[74],"policy":[76,91],"takes":[77],"role":[79],"heuristic.":[84],"Importantly,":[85],"our":[86,106],"method":[87,107],"allows":[88],"simulation":[94],"one":[96],"language":[97],"be":[99],"transferred":[100],"other":[102],"languages.":[103],"We":[104],"demonstrate":[105],"cross-lingual":[109],"named":[110],"entity":[111],"recognition,":[112],"observing":[113],"uniform":[114],"improvements":[115],"over":[116],"traditional":[117],"learning.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":45},{"year":2020,"cited_by_count":48},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}