{"id":"https://openalex.org/W2076799934","doi":"https://doi.org/10.1145/2361354.2361404","title":"Full-text search on multi-byte encoded documents","display_name":"Full-text search on multi-byte encoded documents","publication_year":2012,"publication_date":"2012-09-04","ids":{"openalex":"https://openalex.org/W2076799934","doi":"https://doi.org/10.1145/2361354.2361404","mag":"2076799934"},"language":"en","primary_location":{"id":"doi:10.1145/2361354.2361404","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2361354.2361404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 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/A5015158455","display_name":"Raymond K. Wong","orcid":"https://orcid.org/0000-0002-9814-6029"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Raymond K. Wong","raw_affiliation_strings":["University of New South Wales, Sydney, Australia","University of New South wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"University of New South wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041442063","display_name":"Fengming Shi","orcid":"https://orcid.org/0000-0002-0000-279X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fengming Shi","raw_affiliation_strings":["University of New South Wales, Sydney, Australia","University of New South wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"University of New South wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059454329","display_name":"Nicole Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nicole Lam","raw_affiliation_strings":["University of New South Wales, Sydney, Australia","University of New South wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"University of New South wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015158455"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.11384961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"227","last_page":"236"},"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":0.9864000082015991,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9790999889373779,"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/byte","display_name":"Byte","score":0.8721755743026733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8591839075088501},{"id":"https://openalex.org/keywords/full-text-search","display_name":"Full text search","score":0.8164209723472595},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5010421276092529},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45596712827682495},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.43632742762565613},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43598923087120056},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42073720693588257},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3700237572193146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3105735182762146},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.30190548300743103},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20443618297576904},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14650389552116394}],"concepts":[{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.8721755743026733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8591839075088501},{"id":"https://openalex.org/C20228898","wikidata":"https://www.wikidata.org/wiki/Q83540","display_name":"Full text search","level":3,"score":0.8164209723472595},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5010421276092529},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45596712827682495},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.43632742762565613},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43598923087120056},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42073720693588257},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3700237572193146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3105735182762146},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.30190548300743103},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20443618297576904},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14650389552116394},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2361354.2361404","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2361354.2361404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 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":21,"referenced_works":["https://openalex.org/W191231183","https://openalex.org/W1485941238","https://openalex.org/W1502292638","https://openalex.org/W1548907175","https://openalex.org/W1997841190","https://openalex.org/W2047342127","https://openalex.org/W2049652268","https://openalex.org/W2057985970","https://openalex.org/W2100563514","https://openalex.org/W2103441770","https://openalex.org/W2121252285","https://openalex.org/W2129351872","https://openalex.org/W2158322625","https://openalex.org/W2158874082","https://openalex.org/W2159647614","https://openalex.org/W2160484851","https://openalex.org/W2161488606","https://openalex.org/W2621280964","https://openalex.org/W4247053599","https://openalex.org/W4285719527","https://openalex.org/W7048018715"],"related_works":["https://openalex.org/W2076799934","https://openalex.org/W2111281114","https://openalex.org/W2083577879","https://openalex.org/W2148011053","https://openalex.org/W2359796251","https://openalex.org/W2116908113","https://openalex.org/W1590980840","https://openalex.org/W2185038817","https://openalex.org/W1670204394","https://openalex.org/W2035209426"],"abstract_inverted_index":{"The":[0],"Burrows":[1],"Wheeler":[2],"transform":[3],"(BWT)":[4],"has":[5,55,78],"become":[6],"popular":[7],"in":[8,97],"text":[9,31,50,109,117],"compression,":[10],"full-text":[11,26,94],"search,":[12],"XML":[13],"representation,":[14],"and":[15,61,135],"DNA":[16],"sequence":[17],"matching.":[18],"It":[19],"is":[20],"very":[21],"efficient":[22,93],"to":[23,38,85,104,126],"perform":[24],"a":[25],"search":[27,107,133],"on":[28,45,58,67,83,88],"BWT":[29,44,57,62,87,129],"encoded":[30,47,90],"using":[32,115],"backward":[33,106],"search.":[34,95],"This":[35],"paper":[36],"aims":[37],"study":[39,82],"different":[40],"approaches":[41],"for":[42,92],"applying":[43],"multi-byte":[46,68,89,108],"(e.g.":[48],"UTF-16)":[49],"documents.":[51,110,118],"While":[52],"previous":[53],"work":[54],"studied":[56],"word-based":[59],"models,":[60],"can":[63],"be":[64],"applied":[65],"directly":[66],"encodings":[69],"(by":[70],"treating":[71],"the":[72,127],"document":[73],"as":[74],"single-byte":[75],"coded),":[76],"there":[77],"been":[79],"no":[80],"extensive":[81],"how":[84],"utilize":[86],"documents":[91],"Therefore,":[96],"this":[98],"paper,":[99],"we":[100],"propose":[101],"several":[102],"ways":[103],"efficiently":[105],"We":[111],"demonstrate":[112],"our":[113,124],"findings":[114],"Chinese":[116],"Our":[119],"experiment":[120],"results":[121],"show":[122],"that":[123],"extensions":[125],"standard":[128],"method":[130],"offer":[131],"faster":[132],"performance":[134],"use":[136],"less":[137],"runtime":[138],"memory.":[139]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}