{"id":"https://openalex.org/W2946993860","doi":"https://doi.org/10.5220/0007723602080215","title":"Schema Matching with Frequent Changes on Semi-Structured Input Files: A Machine Learning Approach on Biological Product Data","display_name":"Schema Matching with Frequent Changes on Semi-Structured Input Files: A Machine Learning Approach on Biological Product Data","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2946993860","doi":"https://doi.org/10.5220/0007723602080215","mag":"2946993860"},"language":"en","primary_location":{"id":"doi:10.5220/0007723602080215","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007723602080215","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0007723602080215","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013024092","display_name":"Oliver Schmidts","orcid":null},"institutions":[{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver Schmidts","raw_affiliation_strings":["FH Aachen, University of Applied Sciences and Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FH Aachen, University of Applied Sciences and Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078576521","display_name":"Bodo Kraft","orcid":null},"institutions":[{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bodo Kraft","raw_affiliation_strings":["FH Aachen, University of Applied Sciences and Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FH Aachen, University of Applied Sciences and Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015239826","display_name":"Ines Siebigteroth","orcid":null},"institutions":[{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ines Siebigteroth","raw_affiliation_strings":["FH Aachen, University of Applied Sciences and Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FH Aachen, University of Applied Sciences and Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056244231","display_name":"Albert Z\u00fcndorf","orcid":null},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Albert Z\u00fcndorf","raw_affiliation_strings":["University of Kassel and Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Kassel and Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I106157433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3469,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91731763,"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":"208","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.982200026512146,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9772999882698059,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.7700058817863464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7650212049484253},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7065721750259399},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5077789425849915},{"id":"https://openalex.org/keywords/schema-evolution","display_name":"Schema evolution","score":0.4846137464046478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42848631739616394},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.41619381308555603},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.391221284866333},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36004066467285156},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.346083402633667},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.33832815289497375},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3210393190383911},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.31878662109375},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.22468975186347961},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07749229669570923}],"concepts":[{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.7700058817863464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7650212049484253},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7065721750259399},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5077789425849915},{"id":"https://openalex.org/C2780660560","wikidata":"https://www.wikidata.org/wiki/Q3951893","display_name":"Schema evolution","level":4,"score":0.4846137464046478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42848631739616394},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.41619381308555603},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.391221284866333},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36004066467285156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.346083402633667},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33832815289497375},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3210393190383911},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.31878662109375},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.22468975186347961},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07749229669570923},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0007723602080215","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007723602080215","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Enterprise Information Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0007723602080215","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0007723602080215","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Enterprise Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"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/W49842380","https://openalex.org/W3208717180","https://openalex.org/W2585807518","https://openalex.org/W2125859764","https://openalex.org/W1995017804","https://openalex.org/W2031254074","https://openalex.org/W1545286006","https://openalex.org/W2406112091","https://openalex.org/W2014400548"],"abstract_inverted_index":{"For":[0],"small":[1,130],"to":[2,45,67,74,117,131],"medium":[3,132],"sized":[4,133],"enterprises":[5],"matching":[6,54,93],"schemas":[7],"is":[8,24,115],"still":[9],"a":[10,56,62,88],"time":[11],"consuming":[12],"manual":[13],"task.":[14,58],"Even":[15],"expensive":[16],"commercial":[17],"solutions":[18],"perform":[19],"poorly,":[20],"if":[21],"the":[22,28,70,119],"context":[23],"not":[25],"suitable":[26],"for":[27,121,129],"product.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,60],"provide":[34,61],"an":[35],"approach":[36,66,114],"based":[37,94],"on":[38,95],"concept":[39,96],"name":[40,97],"learning":[41,82,90],"from":[42],"known":[43],"transformations":[44],"discover":[46],"correspondences":[47],"between":[48],"two":[49],"schemas.":[50],"We":[51],"solve":[52],"schema":[53,92],"as":[55],"classification":[57,71],"Additionally,":[59],"named":[63,75],"entity":[64,76],"recognition":[65],"analyze,":[68],"how":[69],"task":[72],"relates":[73],"recognition.":[77],"Benchmarking":[78],"against":[79],"other":[80,101],"machine":[81],"models":[83],"shows":[84],"that":[85],"when":[86],"choosing":[87],"good":[89],"model,":[91],"similarity":[98],"can":[99],"outperform":[100],"approaches":[102],"and":[103,110],"complex":[104,125],"algorithms":[105],"in":[106],"terms":[107],"of":[108,124],"precision":[109],"F1-measure.":[111],"Hence,":[112],"our":[113],"able":[116],"build":[118],"foundation":[120],"improved":[122],"automation":[123],"data":[126],"integration":[127],"applications":[128],"enterprises.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}