{"id":"https://openalex.org/W2123065987","doi":"https://doi.org/10.3115/v1/p14-2081","title":"Two-Stage Hashing for Fast Document Retrieval","display_name":"Two-Stage Hashing for Fast Document Retrieval","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2123065987","doi":"https://doi.org/10.3115/v1/p14-2081","mag":"2123065987"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p14-2081","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2081","pdf_url":"https://aclanthology.org/P14-2081.pdf","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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/P14-2081.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100348559","display_name":"Hao Li","orcid":"https://orcid.org/0000-0002-1758-5936"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Li","raw_affiliation_strings":["Computer Science Department, Rensselaer Polytechnic Institute, Troy, NY, USA","Rensselaer Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","Rensselaer Polytechnic Institute"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"Rensselaer Polytechnic Institute","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075033889","display_name":"Heng Ji","orcid":"https://orcid.org/0000-0002-0464-7966"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Ji","raw_affiliation_strings":["Computer Science Department, Rensselaer Polytechnic Institute, Troy, NY, USA","IBM, ,"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Rensselaer Polytechnic Institute, Troy, NY, USA","institution_ids":["https://openalex.org/I165799507"]},{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100348559"],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":1.9771,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.8964831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":1.0,"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":0.991100013256073,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9889000058174133,"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/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.9048503637313843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8178468346595764},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.6976485252380371},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.6628307700157166},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5965201258659363},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.5850379467010498},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5300224423408508},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5218814015388489},{"id":"https://openalex.org/keywords/sublinear-function","display_name":"Sublinear function","score":0.4436587989330292},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4232885539531708},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3916779160499573},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.3238585591316223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3170168399810791},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23568031191825867},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09313035011291504}],"concepts":[{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.9048503637313843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8178468346595764},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.6976485252380371},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.6628307700157166},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5965201258659363},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.5850379467010498},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5300224423408508},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5218814015388489},{"id":"https://openalex.org/C117160843","wikidata":"https://www.wikidata.org/wiki/Q338652","display_name":"Sublinear function","level":2,"score":0.4436587989330292},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4232885539531708},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3916779160499573},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.3238585591316223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3170168399810791},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23568031191825867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09313035011291504},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/p14-2081","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2081","pdf_url":"https://aclanthology.org/P14-2081.pdf","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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.643.6093","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.643.6093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.columbia.edu/~wliu/ACL14_twostage_hash.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/p14-2081","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p14-2081","pdf_url":"https://aclanthology.org/P14-2081.pdf","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 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3693556586","display_name":null,"funder_award_id":"2-004","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3911920403","display_name":null,"funder_award_id":"FA8750-13-2-0041","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G523448137","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7561134949","display_name":null,"funder_award_id":"W911NF-09-2-0053","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8883859527","display_name":"CAREER:  Cross-Document Cross-Lingual Event Extraction and Tracking","funder_award_id":"0953149","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2123065987.pdf","grobid_xml":"https://content.openalex.org/works/W2123065987.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1484703468","https://openalex.org/W1605873790","https://openalex.org/W1868971014","https://openalex.org/W1974647172","https://openalex.org/W1990537115","https://openalex.org/W1992371516","https://openalex.org/W2012833704","https://openalex.org/W2038276547","https://openalex.org/W2081193615","https://openalex.org/W2098162425","https://openalex.org/W2100874516","https://openalex.org/W2122056984","https://openalex.org/W2122146326","https://openalex.org/W2140427797","https://openalex.org/W2145607950","https://openalex.org/W2147152072","https://openalex.org/W2152925220","https://openalex.org/W2154956324","https://openalex.org/W2188403848","https://openalex.org/W2251864938","https://openalex.org/W2293597654","https://openalex.org/W4230940751","https://openalex.org/W6630737080"],"related_works":["https://openalex.org/W2148008870","https://openalex.org/W2381195555","https://openalex.org/W4246757943","https://openalex.org/W3094967175","https://openalex.org/W2166822184","https://openalex.org/W3096071782","https://openalex.org/W2902799860","https://openalex.org/W4289129280","https://openalex.org/W2754607325","https://openalex.org/W2901290148"],"abstract_inverted_index":{"This":[0],"work":[1],"fulfills":[2],"sublinear":[3],"time":[4],"Nearest":[5],"Neighbor":[6],"Search":[7],"(NNS)":[8],"in":[9,99,117],"massivescale":[10],"document":[11,77,88],"collections.":[12],"The":[13,79],"primary":[14],"contribution":[15],"is":[16],"to":[17,75],"propose":[18],"a":[19,109],"two-stage":[20],"unsupervised":[21],"hashing":[22,29,63,86],"framework":[23,64],"which":[24],"harmoniously":[25],"integrates":[26],"two":[27],"state-of-theart":[28],"algorithms":[30],"Locality":[31],"Sensitive":[32],"Hashing":[33],"(LSH)":[34],"and":[35,50,69,106],"Iterative":[36],"Quantization":[37],"(ITQ).":[38],"LSH":[39],"accounts":[40],"for":[41],"neighbor":[42,55],"candidate":[43],"pruning,":[44],"while":[45],"ITQ":[46],"provides":[47],"an":[48],"efficient":[49],"effective":[51],"reranking":[52],"over":[53,112],"the":[54,61,93],"pool":[56],"captured":[57],"by":[58],"LSH.":[59],"Furthermore,":[60],"proposed":[62],"capitalizes":[65],"on":[66],"both":[67],"term":[68],"topic":[70],"similarity":[71],"among":[72],"documents,":[73,105],"leading":[74],"precise":[76],"retrieval.":[78],"experimental":[80],"results":[81],"convincingly":[82],"show":[83],"that":[84],"our":[85],"based":[87],"retrieval":[89],"approach":[90],"well":[91],"approximates":[92],"conventional":[94],"Information":[95],"Retrieval":[96],"(IR)":[97],"method":[98],"terms":[100],"of":[101,111,115],"retrieving":[102],"semantically":[103],"similar":[104],"meanwhile":[107],"achieves":[108],"speedup":[110],"one":[113],"order":[114],"magnitude":[116],"query":[118],"time.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}