{"id":"https://openalex.org/W2108737429","doi":"https://doi.org/10.1145/2457317.2457386","title":"Scalable string similarity search/join with approximate seeds and multiple backtracking","display_name":"Scalable string similarity search/join with approximate seeds and multiple backtracking","publication_year":2013,"publication_date":"2013-03-18","ids":{"openalex":"https://openalex.org/W2108737429","doi":"https://doi.org/10.1145/2457317.2457386","mag":"2108737429"},"language":"en","primary_location":{"id":"doi:10.1145/2457317.2457386","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2457317.2457386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Joint EDBT/ICDT 2013 Workshops","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/A5053167866","display_name":"Enrico Siragusa","orcid":"https://orcid.org/0000-0002-5943-7544"},"institutions":[{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Enrico Siragusa","raw_affiliation_strings":["Freie Universit\u00e4t Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Freie Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I75951250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109635218","display_name":"David Weese","orcid":"https://orcid.org/0009-0005-3964-5353"},"institutions":[{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Weese","raw_affiliation_strings":["Freie Universit\u00e4t Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Freie Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I75951250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078948324","display_name":"Knut Reinert","orcid":"https://orcid.org/0000-0003-3078-8129"},"institutions":[{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Knut Reinert","raw_affiliation_strings":["Freie Universit\u00e4t Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Freie Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I75951250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053167866"],"corresponding_institution_ids":["https://openalex.org/I75951250"],"apc_list":null,"apc_paid":null,"fwci":2.4712,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.90633702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"370","last_page":"374"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"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":0.9998999834060669,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9916999936103821,"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/backtracking","display_name":"Backtracking","score":0.9167020916938782},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.8085558414459229},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7084612250328064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6777685880661011},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6557135581970215},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5837376117706299},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5193660855293274},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38602566719055176},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.31507623195648193},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2820976972579956},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.21179074048995972},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1865968406200409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1695578396320343}],"concepts":[{"id":"https://openalex.org/C156884757","wikidata":"https://www.wikidata.org/wiki/Q798554","display_name":"Backtracking","level":2,"score":0.9167020916938782},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.8085558414459229},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7084612250328064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777685880661011},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6557135581970215},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5837376117706299},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5193660855293274},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38602566719055176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31507623195648193},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2820976972579956},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.21179074048995972},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1865968406200409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1695578396320343},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":2,"locations":[{"id":"doi:10.1145/2457317.2457386","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2457317.2457386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Joint EDBT/ICDT 2013 Workshops","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.429.1651","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.429.1651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.edbt.org/Proceedings/2013-Genova/papers/workshops/a59-siragusa.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":21,"referenced_works":["https://openalex.org/W109756832","https://openalex.org/W938539187","https://openalex.org/W1834151548","https://openalex.org/W1969173824","https://openalex.org/W1986324942","https://openalex.org/W1990061958","https://openalex.org/W1990413869","https://openalex.org/W2059513841","https://openalex.org/W2074231493","https://openalex.org/W2075996757","https://openalex.org/W2077333702","https://openalex.org/W2097571242","https://openalex.org/W2100751585","https://openalex.org/W2103441770","https://openalex.org/W2129714591","https://openalex.org/W2133687564","https://openalex.org/W2134283755","https://openalex.org/W2155512447","https://openalex.org/W2168459716","https://openalex.org/W2533248932","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2760348722","https://openalex.org/W2783885583","https://openalex.org/W2120095724","https://openalex.org/W2368326437","https://openalex.org/W1631221657","https://openalex.org/W2357479099","https://openalex.org/W2364309619","https://openalex.org/W1525406239","https://openalex.org/W2371864976","https://openalex.org/W3214148052"],"abstract_inverted_index":{"We":[0],"present":[1],"in":[2,21,97],"this":[3],"paper":[4],"scalable":[5],"algorithms":[6],"for":[7,28,52],"optimal":[8],"string":[9,87],"similarity":[10,88],"search":[11,89],"and":[12,37,50,90,99,114],"join.":[13],"Our":[14,93],"methods":[15,51,83],"are":[16,45],"variations":[17],"of":[18,42,72,77],"those":[19],"applied":[20],"Masai":[22],"[15],":[23],"our":[24,43],"recently":[25],"published":[26],"tool":[27,94],"mapping":[29],"high-throughput":[30],"DNA":[31],"sequencing":[32],"data":[33],"with":[34,47],"unpreceded":[35],"speed":[36,85],"accuracy.":[38],"The":[39,105],"key":[40],"features":[41],"approach":[44],"filtration":[46,62],"approximate":[48],"seeds":[49],"multiple":[53],"backtracking.":[54],"Approximate":[55],"seeds,":[56,60],"compared":[57],"to":[58],"exact":[59],"increase":[61],"specificity":[63],"while":[64],"preserving":[65],"sensitivity.":[66],"Multiple":[67],"backtracking":[68],"amortizes":[69],"the":[70,102,111],"cost":[71],"searching":[73],"a":[74],"large":[75],"set":[76],"seeds.":[78],"Combined":[79],"together,":[80],"these":[81],"two":[82],"significantly":[84],"up":[86],"join":[91],"operations.":[92],"is":[95,108],"implemented":[96],"C++":[98],"OpenMP":[100],"using":[101],"SeqAn":[103],"library.":[104],"source":[106],"code":[107],"distributed":[109],"under":[110],"BSD":[112],"license":[113],"can":[115],"be":[116],"freely":[117],"downloaded":[118],"from":[119],"http://www.seqan.de/projects/edbt2013.":[120]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}