{"id":"https://openalex.org/W2051997830","doi":"https://doi.org/10.1145/1008992.1009092","title":"Searching databases for sematically-related schemas","display_name":"Searching databases for sematically-related schemas","publication_year":2004,"publication_date":"2004-07-25","ids":{"openalex":"https://openalex.org/W2051997830","doi":"https://doi.org/10.1145/1008992.1009092","mag":"2051997830"},"language":"en","primary_location":{"id":"doi:10.1145/1008992.1009092","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5028783906","display_name":"Gauri Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gauri Shah","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057284370","display_name":"Tanveer Syeda-Mahmood","orcid":"https://orcid.org/0000-0003-0059-3208"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanveer Syeda-Mahmood","raw_affiliation_strings":["IBM Almaden Research Center, San Jose, CA","IBM Almaden Research Center San Jose , CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, San Jose, CA","institution_ids":["https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden Research Center San Jose , CA","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210085935"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"504","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9997000098228455,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9997000098228455,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9976000189781189,"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/T11719","display_name":"Data Quality and Management","score":0.9927999973297119,"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/computer-science","display_name":"Computer science","score":0.8480803370475769},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.7827134132385254},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7266814112663269},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5180378556251526},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4943368434906006},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4737951159477234},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.46781373023986816},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37659314274787903},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.19504159688949585},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08533880114555359}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8480803370475769},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.7827134132385254},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7266814112663269},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5180378556251526},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4943368434906006},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4737951159477234},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.46781373023986816},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37659314274787903},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.19504159688949585},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08533880114555359}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1008992.1009092","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1008992.1009092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2008896880","https://openalex.org/W2076291573","https://openalex.org/W2081580037","https://openalex.org/W2108489852","https://openalex.org/W2138745488","https://openalex.org/W2139135093","https://openalex.org/W2148572968","https://openalex.org/W2150365753","https://openalex.org/W2156543375","https://openalex.org/W2157060173"],"related_works":["https://openalex.org/W1528218860","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W2144265691","https://openalex.org/W1567515080","https://openalex.org/W1605991620","https://openalex.org/W2259864439","https://openalex.org/W113683524","https://openalex.org/W4387251676","https://openalex.org/W4385261619"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"address":[4,38],"the":[5,39,43,54,60,67],"problem":[6,40],"of":[7,19,41,69],"searching":[8],"schema":[9,44,70],"databases":[10],"for":[11],"semantically-related":[12],"schemas.":[13],"We":[14,36],"first":[15],"give":[16],"a":[17,47,74],"method":[18],"finding":[20],"semantic":[21,48],"similarity":[22],"between":[23],"pair-wise":[24],"schemas":[25,52],"based":[26],"on":[27],"tokenization,":[28],"part-of-speech":[29],"tagging,":[30],"word":[31],"expansion,":[32],"and":[33,63,84],"ontology":[34],"matching.":[35],"then":[37],"indexing":[42],"database":[45,55],"through":[46],"hash":[49],"table.":[50],"Matching":[51],"in":[53,66,77],"are":[56],"found":[57],"by":[58],"hashing":[59],"query":[61],"attributes":[62],"recording":[64],"peaks":[65],"histogram":[68],"hits.":[71],"Results":[72],"indicated":[73],"90%":[75],"improvement":[76],"search":[78],"performance":[79],"while":[80],"maintaining":[81],"high":[82],"precision":[83],"recall.":[85]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
