{"id":"https://openalex.org/W4400529706","doi":"https://doi.org/10.1145/3626772.3657972","title":"Cluster-based Partial Dense Retrieval Fused with Sparse Text Retrieval","display_name":"Cluster-based Partial Dense Retrieval Fused with Sparse Text Retrieval","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400529706","doi":"https://doi.org/10.1145/3626772.3657972"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657972","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657972","pdf_url":null,"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 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3626772.3657972","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032384435","display_name":"Yingrui Yang","orcid":"https://orcid.org/0000-0001-6454-5796"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingrui Yang","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6454-5796","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018045958","display_name":"Parker Carlson","orcid":"https://orcid.org/0000-0003-1856-5088"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parker Carlson","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1856-5088","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037790148","display_name":"Shanxiu He","orcid":"https://orcid.org/0009-0008-8581-6733"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanxiu He","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0009-0008-8581-6733","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074531400","display_name":"Yifan Qiao","orcid":"https://orcid.org/0000-0001-5717-2637"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Qiao","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5717-2637","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060730782","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0003-1902-3387"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["Department of Computer Science, University of California at Santa Barbara, Santa Barbara, California, USA"],"raw_orcid":"https://orcid.org/0000-0003-1902-3387","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California at Santa Barbara, Santa Barbara, California, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":3.0563,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92306005,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2327","last_page":"2331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9923999905586243,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9923999905586243,"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":0.9905999898910522,"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":0.9886000156402588,"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":0.7454660534858704},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5909488797187805},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5441275238990784},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07030618190765381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454660534858704},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5909488797187805},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5441275238990784},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07030618190765381}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3657972","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657972","pdf_url":null,"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 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657972","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657972","pdf_url":null,"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 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2058114682","display_name":null,"funder_award_id":"IIS-2225942","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2150593711","https://openalex.org/W2963469388","https://openalex.org/W2998702515","https://openalex.org/W3145630588","https://openalex.org/W3205509771","https://openalex.org/W4233409427","https://openalex.org/W4252076394","https://openalex.org/W4284664419","https://openalex.org/W4284685333","https://openalex.org/W4284880643","https://openalex.org/W4292433389","https://openalex.org/W4296301204","https://openalex.org/W4367046898","https://openalex.org/W4367047387","https://openalex.org/W4384643607","https://openalex.org/W4384656680","https://openalex.org/W6794609274"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Previous":[0],"work":[1],"has":[2],"demonstrated":[3],"the":[4,56,77,99],"potential":[5],"to":[6,33,74],"combine":[7],"document":[8,63],"rankings":[9],"from":[10],"dense":[11,25,37],"and":[12,38,45,62,66,94,102],"sparse":[13,30,39,59,81],"retrievers":[14],"for":[15,98],"higher":[16],"relevance":[17],"effectiveness.":[18],"This":[19,53,83],"paper":[20,84],"proposes":[21],"a":[22,42,50,69],"cluster-based":[23],"partial":[24],"retrieval":[26,31,40,60,96],"scheme":[27,54,90],"guided":[28],"by":[29],"results":[32,61],"optimize":[34],"fusion":[35],"between":[36],"at":[41],"low":[43],"space":[44],"CPU-time":[46],"cost":[47],"while":[48],"retaining":[49],"competitive":[51],"relevance.":[52],"exploits":[55],"overlap":[57],"of":[58,72,79,88],"embedding":[64],"clusters,":[65],"judiciously":[67],"selects":[68],"limited":[70],"number":[71],"clusters":[73],"probabilistically":[75],"guarantee":[76],"inclusion":[78],"top":[80],"results.":[82],"provides":[85],"an":[86],"evaluation":[87],"this":[89],"on":[91],"its":[92],"in-domain":[93],"zero-shot":[95],"performance":[97],"MS":[100],"MARCO":[101],"BEIR":[103],"datasets.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
