{"id":"https://openalex.org/W3034329167","doi":"https://doi.org/10.1145/3397271.3401099","title":"A Reinforcement Learning Framework for Relevance Feedback","display_name":"A Reinforcement Learning Framework for Relevance Feedback","publication_year":2020,"publication_date":"2020-07-25","ids":{"openalex":"https://openalex.org/W3034329167","doi":"https://doi.org/10.1145/3397271.3401099","mag":"3034329167"},"language":"en","primary_location":{"id":"doi:10.1145/3397271.3401099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006981335","display_name":"Ali Montazeralghaem","orcid":"https://orcid.org/0000-0002-5467-1331"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Montazeralghaem","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101457713","display_name":"Hamed Zamani","orcid":"https://orcid.org/0000-0002-0800-3340"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Zamani","raw_affiliation_strings":["Microsoft, Bellevue, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Bellevue, WA, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034070218","display_name":"James Allan","orcid":"https://orcid.org/0000-0003-0132-5694"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Allan","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.643,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.91663081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"68"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9993000030517578,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/relevance-feedback","display_name":"Relevance feedback","score":0.8880105018615723},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8149393796920776},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7755978107452393},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6997697949409485},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6475481390953064},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6398410797119141},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5005831718444824},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.47719061374664307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45841121673583984},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4205259382724762},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34128209948539734},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.14807388186454773}],"concepts":[{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.8880105018615723},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8149393796920776},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7755978107452393},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6997697949409485},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6475481390953064},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6398410797119141},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5005831718444824},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.47719061374664307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45841121673583984},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4205259382724762},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34128209948539734},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.14807388186454773},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3397271.3401099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3397271.3401099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W112196149","https://openalex.org/W1498436455","https://openalex.org/W1685426458","https://openalex.org/W1964348731","https://openalex.org/W1966093341","https://openalex.org/W1966443646","https://openalex.org/W1972594981","https://openalex.org/W1992113527","https://openalex.org/W2000672666","https://openalex.org/W2040631151","https://openalex.org/W2047221353","https://openalex.org/W2047555304","https://openalex.org/W2049653588","https://openalex.org/W2068905009","https://openalex.org/W2069870183","https://openalex.org/W2093390569","https://openalex.org/W2102046030","https://openalex.org/W2104049510","https://openalex.org/W2107370612","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2132314908","https://openalex.org/W2135728924","https://openalex.org/W2142769902","https://openalex.org/W2156876426","https://openalex.org/W2159859920","https://openalex.org/W2164547069","https://openalex.org/W2169213601","https://openalex.org/W2271840356","https://openalex.org/W2394716307","https://openalex.org/W2468421329","https://openalex.org/W2515351093","https://openalex.org/W2536015822","https://openalex.org/W2539104130","https://openalex.org/W2610935556","https://openalex.org/W2613589950","https://openalex.org/W2740184363","https://openalex.org/W2740384884","https://openalex.org/W2766447205","https://openalex.org/W2799244002","https://openalex.org/W2889658777","https://openalex.org/W2963084599","https://openalex.org/W2963680465","https://openalex.org/W2964121744","https://openalex.org/W3105420278","https://openalex.org/W4214717370","https://openalex.org/W4243333943"],"related_works":["https://openalex.org/W2121179064","https://openalex.org/W1970945111","https://openalex.org/W2386201655","https://openalex.org/W1967770981","https://openalex.org/W4246004437","https://openalex.org/W4381744813","https://openalex.org/W2149778739","https://openalex.org/W2142187719","https://openalex.org/W2098102694","https://openalex.org/W2177103841"],"abstract_inverted_index":{"We":[0],"present":[1],"RML,":[2],"the":[3,41,87,105,118],"first":[4],"known":[5],"general":[6],"reinforcement":[7],"learning":[8],"framework":[9],"for":[10,74,111],"relevance":[11,80],"feedback":[12,48,62,81,89,102],"that":[13,58,69],"directly":[14,33,72],"optimizes":[15],"any":[16,35],"desired":[17],"retrieval":[18,75],"metric,":[19],"including":[20],"precision-oriented,":[21],"recall-oriented,":[22],"and":[23,50,113,116],"even":[24],"diversity":[25],"metrics:":[26],"RML":[27,42,99,108],"can":[28,45],"be":[29],"easily":[30],"extended":[31],"to":[32,61,100],"optimize":[34,73],"arbitrary":[36],"user":[37],"satisfaction":[38],"signal.":[39],"Using":[40],"framework,":[43],"we":[44],"select":[46],"effective":[47,79],"terms":[49],"weight":[51],"them":[52],"appropriately,":[53],"improving":[54],"on":[55,94,120],"past":[56],"methods":[57,68],"fit":[59],"parameters":[60],"algorithms":[63],"using":[64],"heuristic":[65],"approaches":[66],"or":[67],"do":[70],"not":[71,84],"performance.":[76],"Learning":[77],"an":[78],"model":[82],"is":[83,91],"trivial":[85],"since":[86],"true":[88],"distribution":[90],"unknown.":[92],"Experiments":[93],"standard":[95],"TREC":[96],"collections":[97],"compare":[98],"existing":[101],"algorithms,":[103],"demonstrate":[104],"effectiveness":[106],"of":[107],"at":[109],"optimizing":[110],"MAP":[112],"\u03b1-n":[114],"DCG,":[115],"show":[117],"impact":[119],"related":[121],"measures.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}