{"id":"https://openalex.org/W4412638212","doi":"https://doi.org/10.1145/3734947.3734948","title":"A Weighted Retrieval Model for Large Collections under the Exceedance over Relevant Extremes","display_name":"A Weighted Retrieval Model for Large Collections under the Exceedance over Relevant Extremes","publication_year":2024,"publication_date":"2024-12-12","ids":{"openalex":"https://openalex.org/W4412638212","doi":"https://doi.org/10.1145/3734947.3734948"},"language":"en","primary_location":{"id":"doi:10.1145/3734947.3734948","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3734947.3734948","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3734947.3734948","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 16th Annual Meeting of the Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3734947.3734948","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025051151","display_name":"Dipannita Podder","orcid":"https://orcid.org/0009-0001-4980-6158"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Dipannita Podder","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, Kharagpur, India"],"raw_orcid":"https://orcid.org/0009-0001-4980-6158","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062553068","display_name":"Jiaul H. Paik","orcid":"https://orcid.org/0000-0003-1550-3586"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jiaul Paik","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, Kharagpur, India"],"raw_orcid":"https://orcid.org/0000-0003-1550-3586","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032809289","display_name":"Pabitra Mitra","orcid":"https://orcid.org/0000-0002-1908-9813"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pabitra Mitra","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, Kharagpur, India"],"raw_orcid":"https://orcid.org/0000-0002-1908-9813","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025051151"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.49450904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"32","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9973999857902527,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6030580401420593},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42052987217903137},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34605878591537476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6030580401420593},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42052987217903137},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34605878591537476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3734947.3734948","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3734947.3734948","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3734947.3734948","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 16th Annual Meeting of the Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3734947.3734948","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3734947.3734948","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3734947.3734948","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 16th Annual Meeting of the Forum for Information Retrieval Evaluation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412638212.pdf","grobid_xml":"https://content.openalex.org/works/W4412638212.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W266671442","https://openalex.org/W1500657154","https://openalex.org/W1539587635","https://openalex.org/W1685426458","https://openalex.org/W1972594981","https://openalex.org/W1993924397","https://openalex.org/W1998559030","https://openalex.org/W1999822363","https://openalex.org/W2009593660","https://openalex.org/W2020929650","https://openalex.org/W2043909051","https://openalex.org/W2047031127","https://openalex.org/W2048045485","https://openalex.org/W2068098598","https://openalex.org/W2069870183","https://openalex.org/W2080068076","https://openalex.org/W2102046030","https://openalex.org/W2105157020","https://openalex.org/W2113640060","https://openalex.org/W2122456939","https://openalex.org/W2269190553","https://openalex.org/W2739484504","https://openalex.org/W2741632195","https://openalex.org/W2899507349","https://openalex.org/W2904202776","https://openalex.org/W2975467803","https://openalex.org/W3122539873","https://openalex.org/W3137305332","https://openalex.org/W4200247715","https://openalex.org/W4200605863","https://openalex.org/W4206765718","https://openalex.org/W4251326898","https://openalex.org/W4306796052","https://openalex.org/W4387571786","https://openalex.org/W4390746675"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Existing":[0],"probabilistic":[1,92],"retrieval":[2,93,151],"models":[3,14],"rank":[4],"documents":[5,20,111,187],"based":[6],"on":[7,37,62,140],"the":[8,16,49,55,63,66,97,102,123,146,167,173,183,189],"normalized":[9,106],"frequency":[10,29],"of":[11,19,51,65,99,105,112,115,165,169,185],"query":[12],"terms.These":[13],"overestimate":[15],"relevance":[17],"score":[18],"containing":[21],"overrepresented":[22,130,170],"terms":[23,53,131,158,171],"that":[24,145],"appear":[25],"with":[26,156],"extremely":[27],"high":[28],"in":[30,54,81,109,122,154,172],"large":[31,141],"web":[32],"document":[33],"collections.The":[34],"past":[35],"work":[36],"Information":[38],"Retrieval":[39],"(IR)":[40],"targeting":[41],"this":[42,86],"problem":[43],"uses":[44],"truncated":[45],"distributions":[46],"to":[47,76,129,135],"mitigate":[48],"impact":[50],"high-frequency":[52,157],"ranking":[56,124,174],"function.However,":[57],"its":[58],"effectiveness":[59],"heavily":[60],"relies":[61],"selection":[64],"correct":[67],"truncation":[68,78],"point,":[69],"as":[70],"an":[71],"incorrect":[72],"choice":[73],"can":[74],"lead":[75],"aggressive":[77],"and":[79,132,143,159],"result":[80],"missing":[82],"many":[83],"relevant":[84,110,186],"documents.In":[85],"work,":[87],"we":[88],"propose":[89],"a":[90,113,177],"weighted":[91],"model":[94,119,148,162],"by":[95],"modeling":[96],"probability":[98],"exceedance":[100],"over":[101],"maximum":[103],"values":[104],"term":[107],"frequencies":[108],"set":[114],"training":[116],"queries.The":[117],"proposed":[118,147,161],"assigns":[120],"weights":[121,128,134],"function,":[125],"giving":[126],"lower":[127],"higher":[133],"other":[136],"terms.We":[137],"conduct":[138],"experiments":[139],"collections":[142],"show":[144],"outperforms":[149],"state-of-the-art":[150],"models,":[152],"especially":[153],"datasets":[155],"spam.The":[160],"is":[163],"capable":[164],"reducing":[166],"effect":[168],"function":[175],"using":[176],"soft":[178],"scoring":[179],"method,":[180],"thereby":[181],"preventing":[182],"rejection":[184],"from":[188],"ranked":[190],"list.":[191]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}