{"id":"https://openalex.org/W2508603705","doi":"https://doi.org/10.1145/2960811.2967161","title":"Frequent Multi-Byte Character Subtring Extraction using a Succinct Data Structure","display_name":"Frequent Multi-Byte Character Subtring Extraction using a Succinct Data Structure","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2508603705","doi":"https://doi.org/10.1145/2960811.2967161","mag":"2508603705"},"language":"en","primary_location":{"id":"doi:10.1145/2960811.2967161","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2960811.2967161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM Symposium on Document Engineering","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/A5073917520","display_name":"Phanucheep Chotnithi","orcid":null},"institutions":[{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Phanucheep Chotnithi","raw_affiliation_strings":["SOKENDAI (The Graduate University for Advanced Studies), Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"SOKENDAI (The Graduate University for Advanced Studies), Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087434029","display_name":"Atsuhiro Takasu","orcid":"https://orcid.org/0000-0002-9061-7949"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuhiro Takasu","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073917520"],"corresponding_institution_ids":["https://openalex.org/I200475212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04782295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"106"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9929999709129333,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9886999726295471,"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":0.8345059752464294},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.7489190101623535},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.7334497570991516},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6948996782302856},{"id":"https://openalex.org/keywords/generalized-suffix-tree","display_name":"Generalized suffix tree","score":0.6843624711036682},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.6053234338760376},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5628852844238281},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5217717289924622},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.5184523463249207},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.5140761137008667},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4520235061645508},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.4183815121650696},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36448195576667786},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3484387993812561},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3351559638977051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3342241644859314},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12258809804916382},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10077691078186035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345059752464294},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.7489190101623535},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.7334497570991516},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6948996782302856},{"id":"https://openalex.org/C118146561","wikidata":"https://www.wikidata.org/wiki/Q5532514","display_name":"Generalized suffix tree","level":4,"score":0.6843624711036682},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6053234338760376},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5628852844238281},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5217717289924622},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.5184523463249207},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.5140761137008667},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4520235061645508},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.4183815121650696},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36448195576667786},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3484387993812561},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3351559638977051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3342241644859314},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12258809804916382},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10077691078186035},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2960811.2967161","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2960811.2967161","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W68251067","https://openalex.org/W1489909987","https://openalex.org/W1976682045","https://openalex.org/W2076799934","https://openalex.org/W2086536051","https://openalex.org/W2134696992","https://openalex.org/W2139049212","https://openalex.org/W2158322625","https://openalex.org/W2158874082","https://openalex.org/W2161488606","https://openalex.org/W2169872479","https://openalex.org/W4213138647"],"related_works":["https://openalex.org/W2063841356","https://openalex.org/W2405149725","https://openalex.org/W2003608043","https://openalex.org/W2118703123","https://openalex.org/W1527782099","https://openalex.org/W2067974452","https://openalex.org/W4385595111","https://openalex.org/W1543263356","https://openalex.org/W1749587086","https://openalex.org/W117230746"],"abstract_inverted_index":{"Frequent":[0],"string":[1],"mining":[2],"is":[3,44],"widely":[4],"used":[5],"in":[6],"text":[7,11,18,30],"processing":[8,96],"to":[9,29,69,83],"extract":[10],"features.":[12],"Most":[13],"researchers":[14],"have":[15,25],"focused":[16],"on":[17],"using":[19],"single-byte":[20],"characters.":[21],"Consequently,":[22],"their":[23],"applications":[24],"problems":[26],"when":[27],"applied":[28],"represented":[31],"with":[32,101],"multibyte":[33,50],"characters":[34],"such":[35],"as":[36],"Japanese":[37],"and":[38,74],"Chinese":[39],"text.":[40],"The":[41,108],"main":[42],"drawback":[43],"huge":[45],"memory":[46,72,114],"us-age":[47],"for":[48],"treating":[49],"character":[51],"strings.":[52],"To":[53],"solve":[54],"this":[55],"problem,we":[56],"use":[57],"wavelet":[58],"tree-based":[59],"compressed":[60,105],"suffix":[61,67,106],"arrays":[62],"instead":[63],"of":[64],"the":[65,71,80,91,95,113],"normal":[66],"array":[68],"reduce":[70],"usage,":[73],"a":[75,102],"novel":[76],"technique":[77],"that":[78,90],"utilizes":[79],"rank":[81],"operation":[82],"improve":[84],"runtime":[85],"efficiency.Our":[86],"experimental":[87],"evaluation":[88],"shows":[89],"proposed":[92,109],"method":[93,103,110],"reduces":[94,112],"time":[97],"by":[98,116],"45%":[99],"compared":[100],"usingonly":[104],"arrays.":[107],"also":[111],"usage":[115],"75%.":[117]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}