{"id":"https://openalex.org/W4384643607","doi":"https://doi.org/10.1145/3539618.3591941","title":"A Static Pruning Study on Sparse Neural Retrievers","display_name":"A Static Pruning Study on Sparse Neural Retrievers","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384643607","doi":"https://doi.org/10.1145/3539618.3591941"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591941","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in 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/A5068114632","display_name":"Carlos Lassance","orcid":"https://orcid.org/0000-0002-7754-6656"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos Lassance","raw_affiliation_strings":["Naver Labs Europe, Meylan, France"],"raw_orcid":"https://orcid.org/0000-0002-7754-6656","affiliations":[{"raw_affiliation_string":"Naver Labs Europe, Meylan, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034714310","display_name":"Simon Lupart","orcid":"https://orcid.org/0009-0008-2383-4557"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Lupart","raw_affiliation_strings":["Naver Labs Europe, Meylan, France"],"raw_orcid":"https://orcid.org/0009-0008-2383-4557","affiliations":[{"raw_affiliation_string":"Naver Labs Europe, Meylan, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085566571","display_name":"Herv\u00e9 D\u00e9jean","orcid":"https://orcid.org/0000-0002-9837-5358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herv\u00e9 D\u00e9jean","raw_affiliation_strings":["Naver Labs Europe, Meylan, France"],"raw_orcid":"https://orcid.org/0000-0002-9837-5358","affiliations":[{"raw_affiliation_string":"Naver Labs Europe, Meylan, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031052064","display_name":"St\u00e9phane Clinchant","orcid":"https://orcid.org/0000-0003-2367-8837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"St\u00e9phane Clinchant","raw_affiliation_strings":["Naver Labs Europe, Meylan, France"],"raw_orcid":"https://orcid.org/0000-0003-2367-8837","affiliations":[{"raw_affiliation_string":"Naver Labs Europe, Meylan, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018894843","display_name":"Nicola Tonellotto","orcid":"https://orcid.org/0000-0002-7427-1001"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Tonellotto","raw_affiliation_strings":["University of Pisa, Pisa, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7427-1001","affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1771","last_page":"1775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9864000082015991,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9861000180244446,"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":0.8038451671600342},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7891415357589722},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.682497501373291},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6053067445755005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5310982465744019},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4999964237213135},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48382702469825745},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44150227308273315},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32749414443969727},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.16855239868164062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8038451671600342},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7891415357589722},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.682497501373291},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6053067445755005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310982465744019},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4999964237213135},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48382702469825745},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44150227308273315},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32749414443969727},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.16855239868164062},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3539618.3591941","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arpi.unipi.it:11568/1205608","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1205608","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1535624880","https://openalex.org/W1567493457","https://openalex.org/W2023268471","https://openalex.org/W2078251464","https://openalex.org/W2127899914","https://openalex.org/W2137250554","https://openalex.org/W2998702515","https://openalex.org/W3021397474","https://openalex.org/W3136473512","https://openalex.org/W3154280800","https://openalex.org/W3154755316","https://openalex.org/W3155375847","https://openalex.org/W3155480849","https://openalex.org/W3175111331","https://openalex.org/W3194741792","https://openalex.org/W3197604682","https://openalex.org/W4205951122","https://openalex.org/W4284663260","https://openalex.org/W4284880643","https://openalex.org/W4311609640","https://openalex.org/W4320166864","https://openalex.org/W4385573371"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2913534066","https://openalex.org/W2970375204"],"abstract_inverted_index":{"Sparse":[0],"neural":[1,56,124,162],"retrievers,":[2],"such":[3,50],"as":[4,13,51],"DeepImpact,":[5],"uniCOIL":[6],"and":[7,16,66,108,111],"SPLADE,":[8],"have":[9,58],"been":[10,59],"introduced":[11],"recently":[12],"an":[14],"efficient":[15],"effective":[17,41],"way":[18],"to":[19,27,37,45,61,72,166],"perform":[20],"retrieval":[21,48],"with":[22,100,122,133,149],"inverted":[23,94],"indexes.":[24,171],"They":[25],"aim":[26],"learn":[28],"term":[29],"importance":[30],"and,":[31,140],"in":[32],"some":[33],"cases,":[34],"document":[35,42],"expansions,":[36],"provide":[38],"a":[39,81],"more":[40],"ranking":[43],"compared":[44,71],"traditional":[46],"bag-of-words":[47],"models":[49],"BM25.":[52],"However,":[53],"these":[54,118],"sparse":[55,123],"retrievers":[57],"shown":[60],"increase":[62],"the":[63,88,143,153],"computational":[64],"costs":[65],"latency":[67],"of":[68,84,90],"query":[69,91],"processing":[70,92],"their":[73],"classical":[74],"counterparts.":[75],"To":[76],"mitigate":[77],"this,":[78],"we":[79,112,159],"apply":[80],"well-known":[82],"family":[83],"techniques":[85,119],"for":[86],"boosting":[87],"efficiency":[89],"over":[93,114],"indexes:":[95],"static":[96,102,128],"pruning.":[97],"We":[98],"experiment":[99],"three":[101],"pruning":[103,129],"strategies,":[104],"namely":[105],"document-centric,":[106],"term-centric":[107],"agnostic":[109],"pruning,":[110],"assess,":[113],"diverse":[115],"datasets,":[116],"that":[117,161],"still":[120],"work":[121],"retrievers.":[125],"In":[126],"particular,":[127],"achieves":[130],"2x":[131],"speedup":[132,148],"negligible":[134],"effectiveness":[135,154],"loss":[136],"(\u2264":[137,155],"2%":[138],"drop)":[139],"depending":[141],"on":[142,152],"use":[144],"case,":[145],"even":[146],"4x":[147],"minimal":[150],"impact":[151],"8%":[156],"drop).":[157],"Moreover,":[158],"show":[160],"rerankers":[163],"are":[164],"robust":[165],"candidates":[167],"from":[168],"statically":[169],"pruned":[170]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-07-19T00:00:00"}