{"id":"https://openalex.org/W4396812222","doi":"https://doi.org/10.1145/3626772.3657964","title":"PLAID SHIRTTT for Large-Scale Streaming Dense Retrieval","display_name":"PLAID SHIRTTT for Large-Scale Streaming Dense Retrieval","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4396812222","doi":"https://doi.org/10.1145/3626772.3657964"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657964","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657964","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3626772.3657964","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037074105","display_name":"Dawn Lawrie","orcid":"https://orcid.org/0000-0001-7347-7086"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dawn Lawrie","raw_affiliation_strings":["HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":"https://orcid.org/0000-0001-7347-7086","affiliations":[{"raw_affiliation_string":"HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060057841","display_name":"Efsun Sarioglu Kayi","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Efsun Kayi","raw_affiliation_strings":["HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":"https://orcid.org/0000-0002-2357-9807","affiliations":[{"raw_affiliation_string":"HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062016266","display_name":"Eugene Yang","orcid":"https://orcid.org/0000-0002-0051-1535"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Yang","raw_affiliation_strings":["HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":"https://orcid.org/0000-0002-0051-1535","affiliations":[{"raw_affiliation_string":"HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036270568","display_name":"James Mayfield","orcid":"https://orcid.org/0000-0003-3866-3013"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Mayfield","raw_affiliation_strings":["HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA"],"raw_orcid":"https://orcid.org/0000-0003-3866-3013","affiliations":[{"raw_affiliation_string":"HLTCOE, Johns Hopkins University, Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074322406","display_name":"Douglas W. Oard","orcid":"https://orcid.org/0000-0002-1696-0407"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas W. Oard","raw_affiliation_strings":["University of Maryland, College Park, Maryland, USA","HLTCOE, Johns Hopkins University Baltimore, Maryland, USA"],"raw_orcid":"https://orcid.org/0000-0002-1696-0407","affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, Maryland, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"HLTCOE, Johns Hopkins University Baltimore, Maryland, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0668,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76627181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2574","last_page":"2578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9919000267982483,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9919000267982483,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9814000129699707,"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":0.9801999926567078,"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":0.7269349694252014},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5847707390785217},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3807852566242218},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06886598467826843},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0558830201625824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269349694252014},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5847707390785217},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3807852566242218},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06886598467826843},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0558830201625824}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3626772.3657964","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657964","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"},{"id":"pmh:oai:arXiv.org:2405.00975","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.00975","pdf_url":"https://arxiv.org/pdf/2405.00975","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657964","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657964","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2046456023","https://openalex.org/W2088004917","https://openalex.org/W2089379373","https://openalex.org/W2142966412","https://openalex.org/W2595551253","https://openalex.org/W2915063781","https://openalex.org/W2945127593","https://openalex.org/W3021397474","https://openalex.org/W3035390927","https://openalex.org/W3099446234","https://openalex.org/W3134665270","https://openalex.org/W3217305727","https://openalex.org/W4213009331","https://openalex.org/W4306317212","https://openalex.org/W4327644092","https://openalex.org/W6607721473","https://openalex.org/W6831594568"],"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":{"PLAID,":[0],"an":[1],"efficient":[2],"implementation":[3],"of":[4,66,90,117],"the":[5,74,110,115,122,129,134],"ColBERT":[6,29,130],"late":[7],"interaction":[8],"bi-encoder":[9],"using":[10,98],"pretrained":[11],"language":[12],"models":[13],"for":[14,121],"ranking,":[15],"consistently":[16],"achieves":[17],"state-of-the-art":[18],"performance":[19,54],"in":[20,50,56,133],"monolingual,":[21],"cross-language,":[22],"and":[23,35,109,132],"multilingual":[24,111,135],"retrieval.":[25],"PLAID":[26,47,82],"differs":[27],"from":[28],"by":[30,73,128],"assigning":[31],"terms":[32,38],"to":[33,78,126],"clusters":[34],"representing":[36],"those":[37],"as":[39],"cluster":[40,80],"centroids":[41],"plus":[42],"compressed":[43],"residual":[44],"vectors.":[45],"While":[46],"is":[48],"effective":[49],"batch":[51],"experiments,":[52],"its":[53],"degrades":[55],"streaming":[57],"settings":[58],"where":[59],"documents":[60],"arrive":[61],"over":[62],"time":[63],"because":[64],"representations":[65],"new":[67],"tokens":[68,76],"may":[69],"be":[70],"poorly":[71],"modeled":[72],"earlier":[75],"used":[77],"select":[79],"centroids.":[81],"Streaming":[83],"Hierarchical":[84],"Indexing":[85],"that":[86],"Runs":[87],"on":[88,103,107],"Terabytes":[89],"Temporal":[91],"Text":[92],"(PLAID":[93],"HIRTTT)":[94],"addresses":[95],"this":[96,118],"concern":[97],"multi-phase":[99],"incremental":[100],"indexing":[101],"based":[102],"hierarchical":[104],"sharding.":[105],"Experiments":[106],"ClueWeb09":[108],"NeuCLIR":[112],"collection":[113,124],"demonstrate":[114],"effectiveness":[116],"approach":[119],"both":[120],"largest":[123],"indexed":[125],"date":[127],"architecture":[131],"setting,":[136],"respectively.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}