{"id":"https://openalex.org/W2034669757","doi":"https://doi.org/10.5220/0004990102130222","title":"Instance Based Schema Matching Framework Utilizing Google Similarity and Regular Expression","display_name":"Instance Based Schema Matching Framework Utilizing Google Similarity and Regular Expression","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2034669757","doi":"https://doi.org/10.5220/0004990102130222","mag":"2034669757"},"language":"en","primary_location":{"id":"doi:10.5220/0004990102130222","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0004990102130222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 3rd International Conference on Data Management Technologies and Applications","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/A5051322498","display_name":"Osama A. Mehdi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Osama A. Mehdi","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, Malaysia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000398352","display_name":"Hamidah Ibrahim","orcid":"https://orcid.org/0000-0002-9900-0531"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hamidah Ibrahim","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, Malaysia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077876182","display_name":"Lilly Suriani Affendey","orcid":"https://orcid.org/0000-0001-7947-8792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lilly Suriani Affendey","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, Malaysia"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, Malaysia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051322498"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.0807241,"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":"213","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.8306218981742859},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7116027474403381},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.6632330417633057},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.6009810566902161},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5372348427772522},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47777092456817627},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4762704074382782},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46813878417015076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3638492822647095},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33518314361572266},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17185798287391663},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1258927285671234},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.09959614276885986},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08240604400634766}],"concepts":[{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.8306218981742859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7116027474403381},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.6632330417633057},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6009810566902161},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5372348427772522},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47777092456817627},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4762704074382782},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46813878417015076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3638492822647095},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33518314361572266},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17185798287391663},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1258927285671234},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.09959614276885986},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08240604400634766},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0004990102130222","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0004990102130222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 3rd International Conference on Data Management Technologies and Applications","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":0,"referenced_works":[],"related_works":["https://openalex.org/W1528218860","https://openalex.org/W3208717180","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W2185224148","https://openalex.org/W2014400548","https://openalex.org/W2034669757","https://openalex.org/W4301779090","https://openalex.org/W2029826694","https://openalex.org/W4298139853"],"abstract_inverted_index":{"Schema":[0],"matching":[1],"is":[2,183],"the":[3,25,57,62,66,84,99,102,114,132,135,146,162,194],"task":[4],"of":[5,18,28,53,65,86,101,116,121,134,148,164,196,202],"identifying":[6],"correspondences":[7],"between":[8,119],"schema":[9,188],"attributes":[10],"that":[11,144,180],"exist":[12],"in":[13,193,200],"different":[14],"schemas.":[15],"A":[16],"variety":[17],"approaches":[19,42,55],"have":[20],"been":[21],"proposed":[22],"to":[23,34,45,93,96,185],"achieve":[24,46],"main":[26],"goal":[27],"high-quality":[29],"match":[30,49,87,103],"results":[31,178],"with":[32,78,190],"respect":[33],"precision":[35,203],"(P)":[36],"and":[37,123,154,207],"recall":[38,205],"(R).":[39],"However,":[40],"these":[41,54],"are":[43],"unable":[44],"high":[47,191],"quality":[48,85,100],"results,":[50],"as":[51,59,150,157],"most":[52],"treated":[56],"instances":[58,80,133],"string":[60],"regardless":[61],"data":[63,175],"types":[64],"instances.":[67],"As":[68],"a":[69,110,151],"consequence,":[70],"this":[71,106,138],"causes":[72],"unidentii??ed":[73],"matches":[74,118,189],"especially":[75],"for":[76,112,137],"attribute":[77],"numeric":[79],"which":[81],"further":[82,97],"reduces":[83],"results.":[88,104],"Therefore,":[89],"effort":[90],"still":[91],"needs":[92],"be":[94],"done":[95],"improve":[98],"In":[105],"paper,":[107],"we":[108,128,140,167],"propose":[109],"framework":[111,182],"addressing":[113],"problem":[115],"finding":[117],"schemas":[120,136],"semantically":[122],"syntactically":[124],"related":[125],"data.":[126],"Since":[127],"only":[129],"fully":[130],"exploit":[131],"task,":[139],"rely":[141],"on":[142],"strategies":[143],"combine":[145],"strength":[147],"Google":[149],"web":[152],"semantic":[153],"regular":[155],"expression":[156],"pattern":[158],"recognition.":[159],"To":[160],"demonstrate":[161],"accuracy":[163,192],"our":[165,181],"framework,":[166],"conducted":[168],"an":[169],"experimental":[170],"evaluation":[171],"using":[172],"real":[173],"world":[174],"sets.":[176],"The":[177],"show":[179],"able":[184],"find":[186],"1-1":[187],"range":[195],"93%":[197],"-":[198],"99%":[199],"terms":[201],"(P),":[204],"(R),":[206],"F-measure":[208],"(F).":[209]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}