{"id":"https://openalex.org/W2095057833","doi":"https://doi.org/10.1109/bigdata.2013.6691617","title":"Group-Scheme: SIMD-based compression algorithms for web text data","display_name":"Group-Scheme: SIMD-based compression algorithms for web text data","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2095057833","doi":"https://doi.org/10.1109/bigdata.2013.6691617","mag":"2095057833"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","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/A5100441863","display_name":"Xudong Zhang","orcid":"https://orcid.org/0000-0003-2671-8275"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xudong Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Peking University, Beijing, China","Dept. of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Dept. of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037145565","display_name":"Wayne Xin Zhao","orcid":"https://orcid.org/0000-0002-8333-6196"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wayne Xin Zhao","raw_affiliation_strings":["Department of Computer Science and Technology, Peking University, Beijing, China","Dept. of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Dept. of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026825332","display_name":"Dongdong Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongdong Shan","raw_affiliation_strings":["Department of Computer Science and Technology, Peking University, Beijing, China","Dept. of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Dept. of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111726041","display_name":"Hongfei Yan","orcid":"https://orcid.org/0000-0001-5914-8585"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Yan","raw_affiliation_strings":["Department of Computer Science and Technology, Peking University, Beijing, China","Dept. of Computer Science and Technology, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Dept. of Computer Science and Technology, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100441863"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.9618,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82655377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"525","last_page":"530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9769999980926514,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/simd","display_name":"SIMD","score":0.9448652267456055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8546291589736938},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6237589716911316},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6129575967788696},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.606768786907196},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5119098424911499},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4722639322280884},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4571281969547272},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4490184187889099},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4395093619823456},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4316810667514801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1070813238620758},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07996901869773865}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.9448652267456055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8546291589736938},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6237589716911316},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6129575967788696},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.606768786907196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5119098424911499},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4722639322280884},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4571281969547272},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4490184187889099},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4395093619823456},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4316810667514801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1070813238620758},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07996901869773865},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2013.6691617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1546738280","https://openalex.org/W1985136582","https://openalex.org/W2031780529","https://openalex.org/W2032866865","https://openalex.org/W2128777897","https://openalex.org/W2135828943","https://openalex.org/W2140453381","https://openalex.org/W2144193618","https://openalex.org/W4248415000"],"related_works":["https://openalex.org/W2099629705","https://openalex.org/W2161302774","https://openalex.org/W4383723869","https://openalex.org/W4384298135","https://openalex.org/W4383722264","https://openalex.org/W2388481516","https://openalex.org/W1723410974","https://openalex.org/W3007688875","https://openalex.org/W3209669196","https://openalex.org/W2110517301"],"abstract_inverted_index":{"Compression":[0],"algorithms":[1,59,115],"have":[2,43],"been":[3,44],"quite":[4],"important":[5],"for":[6,34],"data":[7,120],"oriented":[8],"tasks,":[9],"especially":[10],"in":[11,46],"the":[12,57,63,91,113,135],"era":[13],"of":[14,20,86,107],"Big":[15],"Data.":[16],"The":[17],"rapid":[18],"development":[19],"modern":[21],"processors":[22],"facilitates":[23],"us":[24],"with":[25,74],"powerful":[26],"SIMD":[27,38,64,138],"instruction":[28],"sets,":[29],"which":[30,80],"provides":[31],"an":[32],"opportunity":[33],"better":[35],"performance.":[36],"Although":[37],"based":[39],"optimization":[40],"on":[41,55,116,126],"compression":[42,72,87,97,127],"explored":[45],"some":[47],"studies":[48,52],"[2,":[49],"7],":[50],"these":[51],"usually":[53],"focus":[54],"modifying":[56],"existing":[58],"to":[60,82],"fit":[61],"into":[62],"instruction.":[65],"In":[66],"this":[67],"paper,":[68],"we":[69,93],"propose":[70],"a":[71,75,95,104],"framework":[73],"novel":[76,96],"storage":[77],"layout":[78],"format,":[79],"aims":[81],"improve":[83],"instruction-level":[84],"parallelizability":[85],"algorithms.":[88],"By":[89],"instantiating":[90],"framework,":[92],"design":[94],"algorithm":[98,142],"family,":[99],"called":[100,109],"Group-Scheme,":[101,108],"and":[102,129,140],"present":[103],"parallelized":[105],"version":[106],"SIMD-Group-Scheme.":[110],"We":[111],"evaluate":[112],"proposed":[114],"two":[117],"public":[118],"TREC":[119],"sets.":[121],"With":[122],"very":[123],"competitive":[124],"performance":[125],"ratio":[128],"encoding":[130],"speed,":[131],"SIMD-Group-Scheme":[132],"significantly":[133],"outperforms":[134],"implementation":[136],"without":[137],"instructions":[139],"state-of-the-art":[141],"(i.e.":[143],"SIMD-G8IU":[144],"[7]),":[145],"w.r.t":[146],"decoding":[147],"speed.":[148]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}