{"id":"https://openalex.org/W2527905720","doi":"https://doi.org/10.1109/iccse.2016.7581668","title":"Light-weight top-k string similarity search with a two-level inverted index","display_name":"Light-weight top-k string similarity search with a two-level inverted index","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2527905720","doi":"https://doi.org/10.1109/iccse.2016.7581668","mag":"2527905720"},"language":"en","primary_location":{"id":"doi:10.1109/iccse.2016.7581668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccse.2016.7581668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 11th International Conference on Computer Science &amp; Education (ICCSE)","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/A5100698162","display_name":"Yuhui Zheng","orcid":"https://orcid.org/0000-0001-5398-1760"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhui Zheng","raw_affiliation_strings":["Software School, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Software School, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053226181","display_name":"Tianzhi Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzhi Deng","raw_affiliation_strings":["Software School, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Software School, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100456913","display_name":"Xiaoli Wang","orcid":"https://orcid.org/0000-0002-8677-9080"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoli Wang","raw_affiliation_strings":["Software School, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Software School, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100698162"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06236399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"718","last_page":"723"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9987000226974487,"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":0.9987000226974487,"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/T11719","display_name":"Data Quality and Management","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9943000078201294,"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/inverted-index","display_name":"Inverted index","score":0.8196144700050354},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.7795252799987793},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.7407930493354797},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.6767842769622803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6582514643669128},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6120535731315613},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4868175685405731},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.46349096298217773},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.3585640490055084},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32426759600639343},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2669602036476135},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2618423104286194},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.23879557847976685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2020530104637146},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.19881778955459595},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09635263681411743}],"concepts":[{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.8196144700050354},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.7795252799987793},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.7407930493354797},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.6767842769622803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6582514643669128},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6120535731315613},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4868175685405731},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.46349096298217773},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.3585640490055084},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32426759600639343},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2669602036476135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2618423104286194},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.23879557847976685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2020530104637146},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.19881778955459595},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09635263681411743},{"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},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccse.2016.7581668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccse.2016.7581668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 11th International Conference on Computer Science &amp; Education (ICCSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W123495503","https://openalex.org/W1536525420","https://openalex.org/W1591155856","https://openalex.org/W1987869189","https://openalex.org/W2073329022","https://openalex.org/W2094953319","https://openalex.org/W2100097984","https://openalex.org/W2119057313","https://openalex.org/W2123402141","https://openalex.org/W2127675794","https://openalex.org/W2148148676","https://openalex.org/W2167847032","https://openalex.org/W2217456271","https://openalex.org/W2286724461"],"related_works":["https://openalex.org/W2399644331","https://openalex.org/W2187092961","https://openalex.org/W2405436873","https://openalex.org/W2131677984","https://openalex.org/W2527905720","https://openalex.org/W52396946","https://openalex.org/W1973578339","https://openalex.org/W1824878879","https://openalex.org/W1998140328","https://openalex.org/W2462428821"],"abstract_inverted_index":{"Given":[0],"a":[1,5,39,62,66,75],"query":[2,27,64],"string":[3,11,28],"and":[4],"collection":[6,24],"of":[7,49,103],"strings,":[8],"the":[9,17,23,26,81,92,104],"top-k":[10],"similarity":[12],"search":[13],"is":[14,94],"to":[15,25,42,79],"find":[16],"k":[18],"most":[19],"similar":[20],"strings":[21],"in":[22,85],"based":[29],"on":[30,38],"edit":[31,50],"distance.":[32,51],"Most":[33],"existing":[34,90],"works":[35],"have":[36],"focused":[37],"filter-and-verify":[40],"framework":[41],"prune":[43],"non-candidates":[44],"with":[45],"some":[46],"lower":[47],"bounds":[48],"The":[52],"best":[53],"current":[54],"implementations":[55],"require":[56],"more":[57,100],"than":[58,101],"10":[59],"seconds":[60],"answering":[61],"top-40":[63,82],"for":[65],"real":[67],"eBay":[68,83],"dataset.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73,97],"propose":[74],"novel":[76],"light-weight":[77],"algorithm":[78],"answer":[80,93],"queries":[84],"around":[86],"350":[87],"milliseconds.":[88],"Unlike":[89],"work,":[91],"approximate,":[95],"but":[96],"show":[98],"that":[99],"95%":[102],"final":[105],"results":[106],"are":[107],"returned.":[108]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
