{"id":"https://openalex.org/W2021947911","doi":"https://doi.org/10.1145/2009916.2009985","title":"Query by document via a decomposition-based two-level retrieval approach","display_name":"Query by document via a decomposition-based two-level retrieval approach","publication_year":2011,"publication_date":"2011-07-24","ids":{"openalex":"https://openalex.org/W2021947911","doi":"https://doi.org/10.1145/2009916.2009985","mag":"2021947911"},"language":"en","primary_location":{"id":"doi:10.1145/2009916.2009985","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2009985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","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/A5082759729","display_name":"Linkai Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linkai Weng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618669","display_name":"Zhiwei Li","orcid":"https://orcid.org/0000-0002-3378-3457"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Li","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069272117","display_name":"Rui Cai","orcid":"https://orcid.org/0000-0002-6499-2091"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Cai","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069049205","display_name":"Yaoxue Zhang","orcid":"https://orcid.org/0000-0001-6717-461X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoxue Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052528809","display_name":"Yuezhi Zhou","orcid":"https://orcid.org/0000-0002-1850-3007"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuezhi Zhou","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049154222","display_name":"Laurence T. Yang","orcid":"https://orcid.org/0000-0002-7986-4244"},"institutions":[{"id":"https://openalex.org/I197191942","display_name":"St. Francis Xavier University","ror":"https://ror.org/01wcaxs37","country_code":"CA","type":"education","lineage":["https://openalex.org/I197191942"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Laurence T. Yang","raw_affiliation_strings":["St. Francis Xavier University, Antigonish, Canada","St. Francis Xavier University Antigonish, Canada#TAB#"],"affiliations":[{"raw_affiliation_string":"St. Francis Xavier University, Antigonish, Canada","institution_ids":["https://openalex.org/I197191942"]},{"raw_affiliation_string":"St. Francis Xavier University Antigonish, Canada#TAB#","institution_ids":["https://openalex.org/I197191942"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100616189","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-2839-8693"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5082759729"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.091,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.89120218,"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":"505","last_page":"514"},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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/T11269","display_name":"Algorithms and Data Compression","score":0.998199999332428,"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/information-retrieval","display_name":"Information retrieval","score":0.7519263029098511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7463600635528564},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.6333409547805786},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5002439022064209},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4864037334918976}],"concepts":[{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7519263029098511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7463600635528564},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.6333409547805786},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5002439022064209},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4864037334918976},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2009916.2009985","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2009916.2009985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.230.5738","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.230.5738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/152206/QueryByDocument_SIGIR2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W23524565","https://openalex.org/W161736330","https://openalex.org/W190008395","https://openalex.org/W1574901103","https://openalex.org/W1660390307","https://openalex.org/W1880262756","https://openalex.org/W1964348731","https://openalex.org/W1981825277","https://openalex.org/W2001082470","https://openalex.org/W2012833704","https://openalex.org/W2038276547","https://openalex.org/W2042281163","https://openalex.org/W2042980227","https://openalex.org/W2057989089","https://openalex.org/W2066636486","https://openalex.org/W2067432306","https://openalex.org/W2071940869","https://openalex.org/W2073965851","https://openalex.org/W2081533422","https://openalex.org/W2085922539","https://openalex.org/W2107743791","https://openalex.org/W2111593814","https://openalex.org/W2123107811","https://openalex.org/W2130395434","https://openalex.org/W2135029798","https://openalex.org/W2135194391","https://openalex.org/W2137268161","https://openalex.org/W2138662031","https://openalex.org/W2145766604","https://openalex.org/W2147152072","https://openalex.org/W2149943934","https://openalex.org/W2152565070","https://openalex.org/W2153636395","https://openalex.org/W2154610494","https://openalex.org/W2163085258","https://openalex.org/W2169189540","https://openalex.org/W2171836785","https://openalex.org/W4233135949","https://openalex.org/W4285719527","https://openalex.org/W6607826182","https://openalex.org/W6637101025","https://openalex.org/W6639619044","https://openalex.org/W6680012447","https://openalex.org/W7075682605"],"related_works":["https://openalex.org/W2161902337","https://openalex.org/W2363027842","https://openalex.org/W1601704076","https://openalex.org/W2354545733","https://openalex.org/W2373031548","https://openalex.org/W2028114055","https://openalex.org/W1536405386","https://openalex.org/W2357241418","https://openalex.org/W83344948","https://openalex.org/W4220868064"],"abstract_inverted_index":{"Retrieving":[0],"similar":[1],"documents":[2,127,139],"from":[3],"a":[4,10,14,37,54,60,69,73,79,91,123,133],"large-scale":[5],"text":[6],"corpus":[7],"according":[8,128],"to":[9,28,33,68,113,120,129],"given":[11],"document":[12,38,61,65,75,95,145],"is":[13,66],"fundamental":[15],"technique":[16],"for":[17],"many":[18],"applications.":[19],"However,":[20],"most":[21],"of":[22,36,90,125,132],"existing":[23],"indexing":[24],"techniques":[25],"have":[26],"difficulties":[27],"address":[29],"this":[30,50,141],"problem":[31],"due":[32],"special":[34],"properties":[35],"query,":[39],"e.g.":[40],"high":[41],"dimensionality,":[42],"sparse":[43],"representation":[44],"and":[45,72,93],"semantic":[46],"issue.":[47],"Towards":[48],"addressing":[49],"problem,":[51],"we":[52,137],"propose":[53],"two-level":[55],"retrieval":[56],"solution":[57],"based":[58],"on":[59],"decomposition":[62],"idea.":[63],"A":[64],"decomposed":[67],"compact":[70,84,116],"vector":[71,85,131],"few":[74],"specific":[76,96],"keywords":[77,97],"by":[78,143],"dimension":[80,104],"reduction":[81,105],"approach.":[82],"The":[83],"embodies":[86],"the":[87,94,99,115,130],"major":[88],"semantics":[89],"document,":[92],"complement":[98],"discriminative":[100],"power":[101],"lost":[102],"in":[103,140],"process.":[106],"We":[107],"adopt":[108],"locality":[109],"sensitive":[110],"hashing":[111],"(LSH)":[112],"index":[114],"vectors,":[117],"which":[118],"guarantees":[119],"quickly":[121],"find":[122],"set":[124,142],"related":[126],"query":[134],"document.":[135],"Then":[136],"re-rank":[138],"their":[144]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}