{"id":"https://openalex.org/W2025690557","doi":"https://doi.org/10.1145/1571941.1571969","title":"Compressing term positions in web indexes","display_name":"Compressing term positions in web indexes","publication_year":2009,"publication_date":"2009-07-19","ids":{"openalex":"https://openalex.org/W2025690557","doi":"https://doi.org/10.1145/1571941.1571969","mag":"2025690557"},"language":"en","primary_location":{"id":"doi:10.1145/1571941.1571969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1571969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5101914876","display_name":"Hao Yan","orcid":"https://orcid.org/0000-0002-7468-528X"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]},{"id":"https://openalex.org/I90965887","display_name":"SUNY Polytechnic Institute","ror":"https://ror.org/000fxgx19","country_code":"US","type":"education","lineage":["https://openalex.org/I90965887"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Yan","raw_affiliation_strings":["Polytechnic Institute of NYU, Brooklyn, NY, USA","Polytechnic institute of NYU, Brooklyn, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Polytechnic Institute of NYU, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I90965887"]},{"raw_affiliation_string":"Polytechnic institute of NYU, Brooklyn, NY, USA#TAB#","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078621623","display_name":"Shuai Ding","orcid":"https://orcid.org/0009-0001-2744-3018"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]},{"id":"https://openalex.org/I90965887","display_name":"SUNY Polytechnic Institute","ror":"https://ror.org/000fxgx19","country_code":"US","type":"education","lineage":["https://openalex.org/I90965887"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuai Ding","raw_affiliation_strings":["Polytechnic Institute of NYU, Brooklyn, NY, USA","Polytechnic institute of NYU, Brooklyn, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Polytechnic Institute of NYU, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I90965887"]},{"raw_affiliation_string":"Polytechnic institute of NYU, Brooklyn, NY, USA#TAB#","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074323303","display_name":"Torsten Suel","orcid":"https://orcid.org/0000-0002-8324-980X"},"institutions":[{"id":"https://openalex.org/I90965887","display_name":"SUNY Polytechnic Institute","ror":"https://ror.org/000fxgx19","country_code":"US","type":"education","lineage":["https://openalex.org/I90965887"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Torsten Suel","raw_affiliation_strings":["Polytechnic Institute of NYU, Brooklyn, NY, USA","Polytechnic institute of NYU, Brooklyn, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Polytechnic Institute of NYU, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I90965887"]},{"raw_affiliation_string":"Polytechnic institute of NYU, Brooklyn, NY, USA#TAB#","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101914876"],"corresponding_institution_ids":["https://openalex.org/I57206974","https://openalex.org/I90965887"],"apc_list":null,"apc_paid":null,"fwci":10.3875,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.98259131,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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":0.9994000196456909,"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/T11106","display_name":"Data Management and Algorithms","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9980999827384949,"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":0.8637202978134155},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5873364806175232},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5771949291229248},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.564826250076294},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5603762269020081},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5206446051597595},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5112807750701904},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4925549626350403},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.47513774037361145},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.46414318680763245},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4437941610813141},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41367006301879883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11447200179100037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8637202978134155},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5873364806175232},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5771949291229248},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.564826250076294},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5603762269020081},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5206446051597595},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5112807750701904},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4925549626350403},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.47513774037361145},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.46414318680763245},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4437941610813141},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41367006301879883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11447200179100037},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1571941.1571969","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1571969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.155.2695","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.155.2695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cis.poly.edu/~hyan/sigIR-position.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W191231183","https://openalex.org/W1541128204","https://openalex.org/W1559631118","https://openalex.org/W1574036524","https://openalex.org/W1575155361","https://openalex.org/W1591377317","https://openalex.org/W1669813703","https://openalex.org/W1771000076","https://openalex.org/W2015662797","https://openalex.org/W2022292926","https://openalex.org/W2026302857","https://openalex.org/W2038807029","https://openalex.org/W2042130547","https://openalex.org/W2052867877","https://openalex.org/W2058422563","https://openalex.org/W2070507812","https://openalex.org/W2070740689","https://openalex.org/W2076471773","https://openalex.org/W2086348764","https://openalex.org/W2087361130","https://openalex.org/W2115613939","https://openalex.org/W2121353570","https://openalex.org/W2128777897","https://openalex.org/W2138662031","https://openalex.org/W2140453381","https://openalex.org/W2144193618","https://openalex.org/W2160484851","https://openalex.org/W2162432120","https://openalex.org/W2166001746","https://openalex.org/W2427788461","https://openalex.org/W2621280964"],"related_works":["https://openalex.org/W2058987221","https://openalex.org/W2119380317","https://openalex.org/W2070155952","https://openalex.org/W2145657320","https://openalex.org/W2082868123","https://openalex.org/W118734887","https://openalex.org/W2102493899","https://openalex.org/W2367099342","https://openalex.org/W2388346754","https://openalex.org/W4282568653"],"abstract_inverted_index":{"Large":[0],"search":[1,60],"engines":[2],"process":[3],"thousands":[4],"of":[5,11,29,80,84,136,139],"queries":[6],"per":[7],"second":[8],"on":[9,31,52,68],"billions":[10],"pages,":[12],"making":[13,108],"query":[14,35],"processing":[15],"a":[16,27,133,137],"major":[17],"factor":[18],"in":[19,58,77,87,148],"their":[20],"operating":[21],"costs.":[22],"This":[23],"has":[24,66],"led":[25],"to":[26,33,99,111,155],"lot":[28],"research":[30],"how":[32,154],"improve":[34],"throughput,":[36],"using":[37],"techniques":[38,53,143],"such":[39],"as":[40],"massive":[41],"parallelism,":[42],"caching,":[43],"early":[44],"termination,":[45],"and":[46,71,128,141],"inverted":[47],"index":[48],"compression.":[49],"We":[50,131,151],"focus":[51],"for":[54,119,126,144,160],"compressing":[55,69,145],"term":[56,85,96],"positions":[57,86],"web":[59,88,149],"engine":[61],"indexes.":[62,150],"Most":[63],"previous":[64],"work":[65],"focused":[67],"docID":[70,127],"frequency":[72,129],"data,":[73],"or":[74],"position":[75,120,146,158],"information":[76],"other":[78],"types":[79],"text":[81],"collections.":[82],"Compression":[83],"pages":[89],"is":[90],"complicated":[91],"by":[92],"the":[93],"fact":[94],"that":[95,163],"occurrences":[97],"tend":[98],"cluster":[100],"within":[101],"documents":[102],"but":[103],"not":[104],"across":[105],"document":[106],"boundaries,":[107],"it":[109],"harder":[110],"exploit":[112],"clustering":[113],"effects.":[114],"Also,":[115],"typical":[116],"access":[117,157],"patterns":[118],"data":[121,147,159],"are":[122],"different":[123],"from":[124],"those":[125],"data.":[130],"perform":[132],"detailed":[134],"study":[135,153],"number":[138],"existing":[140],"new":[142],"also":[152],"efficiently":[156],"ranking":[161],"functions":[162],"take":[164],"proximity":[165],"features":[166],"into":[167],"account.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":10}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}