{"id":"https://openalex.org/W2889658777","doi":"https://doi.org/10.1145/3234944.3234977","title":"Multi Page Search with Reinforcement Learning to Rank","display_name":"Multi Page Search with Reinforcement Learning to Rank","publication_year":2018,"publication_date":"2018-09-10","ids":{"openalex":"https://openalex.org/W2889658777","doi":"https://doi.org/10.1145/3234944.3234977","mag":"2889658777"},"language":"en","primary_location":{"id":"doi:10.1145/3234944.3234977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3234944.3234977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101427959","display_name":"Wei Zeng","orcid":"https://orcid.org/0009-0006-4437-9042"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zeng","raw_affiliation_strings":["University of Chinese Academy of Sciences & Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020766468","display_name":"Jun Xu","orcid":"https://orcid.org/0000-0001-7170-111X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["University of Chinese Academy of Sciences & Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616866","display_name":"Yanyan Lan","orcid":"https://orcid.org/0000-0002-7811-3262"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Lan","raw_affiliation_strings":["University of Chinese Academy of Sciences & Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088621320","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-9509-8674"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["University of Chinese Academy of Sciences & Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["University of Chinese Academy of Sciences & Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences & Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"175","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976000189781189,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.833055853843689},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.786382794380188},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.744030773639679},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7413411140441895},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.7292603850364685},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.6782569885253906},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.6619734764099121},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6423840522766113},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6245847344398499},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5542282462120056},{"id":"https://openalex.org/keywords/exploratory-search","display_name":"Exploratory search","score":0.49746134877204895},{"id":"https://openalex.org/keywords/metasearch-engine","display_name":"Metasearch engine","score":0.4360368251800537},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.3921501934528351},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31192445755004883},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27457359433174133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2631320357322693},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.11686024069786072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833055853843689},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.786382794380188},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.744030773639679},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7413411140441895},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.7292603850364685},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.6782569885253906},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.6619734764099121},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6423840522766113},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6245847344398499},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5542282462120056},{"id":"https://openalex.org/C2777866876","wikidata":"https://www.wikidata.org/wiki/Q5421358","display_name":"Exploratory search","level":2,"score":0.49746134877204895},{"id":"https://openalex.org/C173979980","wikidata":"https://www.wikidata.org/wiki/Q114106","display_name":"Metasearch engine","level":4,"score":0.4360368251800537},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3921501934528351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31192445755004883},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27457359433174133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2631320357322693},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.11686024069786072},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3234944.3234977","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3234944.3234977","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G6620960268","display_name":null,"funder_award_id":"61773362, 61425016, 61472401, 61722211, 20180290","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1973435495","https://openalex.org/W1974360117","https://openalex.org/W2000672666","https://openalex.org/W2108862644","https://openalex.org/W2127452535","https://openalex.org/W2129245267","https://openalex.org/W2132314908","https://openalex.org/W2143331230","https://openalex.org/W2149427297","https://openalex.org/W2155027007","https://openalex.org/W2164547069","https://openalex.org/W2170518359","https://openalex.org/W2176930994","https://openalex.org/W2257117461","https://openalex.org/W2312609093","https://openalex.org/W2739916191","https://openalex.org/W2740384884","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2186976797","https://openalex.org/W2085256855","https://openalex.org/W2217766582","https://openalex.org/W3210975432","https://openalex.org/W61747831","https://openalex.org/W2299342644","https://openalex.org/W2791713972","https://openalex.org/W2035739021","https://openalex.org/W3155638432","https://openalex.org/W2547614144"],"abstract_inverted_index":{"Web":[0],"search":[1,11,15,20,119,151,161],"engines":[2],"are":[3,25],"typically":[4],"designed":[5],"to":[6,27,76,83,93,99,102,113,140,164,180],"involve":[7,68],"multiple":[8],"pages":[9,38],"of":[10,36,65,86,133,146,194,215,220,226],"results,":[12],"and":[13,176,187,222],"the":[14,48,52,73,78,84,87,122,131,144,160,165,169,173,177,181,185,200,213],"users":[16],"engaging":[17],"in":[18,120,148,158,172],"exploratory":[19],"with":[21],"ad":[22],"hoc":[23],"queries":[24,41],"likely":[26],"access":[28],"more":[29],"than":[30,47],"one":[31],"result":[32,57,135,174],"pages.":[33,58],"The":[34,137,190],"ranking":[35,132,145,218],"web":[37],"for":[39,116,129,167,183,198],"such":[40],"should":[42],"consider":[43],"additional":[44],"information":[45,66,75],"other":[46],"original":[49],"query,":[50],"e.g.,":[51],"user":[53,178],"clicks":[54],"on":[55,205],"previous":[56],"Existing":[59],"methods":[60],"that":[61,209],"utilize":[62],"this":[63,106],"kind":[64],"usually":[67],"relevance":[69,96,217,223],"feedback,":[70],"which":[71,121,159],"uses":[72],"feedback":[74,88,97,124,224],"explore":[77],"user's":[79,123],"intent.":[80],"However,":[81],"due":[82],"limitation":[85],"mechanism,":[89],"it":[90],"is":[91,196],"difficult":[92],"apply":[94],"existing":[95],"techniques":[98],"state-of-the-art":[100],"learning":[101,112,199],"rank":[103,114],"models.":[104],"In":[105],"paper,":[107],"we":[108],"propose":[109],"a":[110,153],"novel":[111],"model":[115,201,219],"multi":[117,149],"page":[118,150],"can":[125],"be":[126],"naturally":[127],"utilized":[128],"improving":[130],"next":[134],"page.":[136],"model,":[138],"referred":[139],"as":[141,152],"MDP-MPS,":[142],"formalizes":[143],"documents":[147],"Markov":[154],"decision":[155],"process":[156],"(MDP)":[157],"engine":[162],"corresponds":[163,179],"agent":[166],"constructing":[168],"document":[170],"rankings":[171,186],"pages,":[175],"environment":[182],"judging":[184],"providing":[188],"rewards.":[189],"policy":[191],"gradient":[192],"algorithm":[193],"REINFORCE":[195],"adopted":[197],"parameters.":[202],"Experimental":[203],"results":[204],"OHSUMED":[206],"dataset":[207],"showed":[208],"our":[210],"approach":[211],"outperformed":[212],"baselines":[214],"traditional":[216],"ListNet":[221],"method":[225],"Rocchio.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}