{"id":"https://openalex.org/W1603620849","doi":"https://doi.org/10.1007/11890850_9","title":"Mapping Physical Formats to Logical Models to Extract Data and Metadata: The Defuddle Parsing Engine","display_name":"Mapping Physical Formats to Logical Models to Extract Data and Metadata: The Defuddle Parsing Engine","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W1603620849","doi":"https://doi.org/10.1007/11890850_9","mag":"1603620849"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/11890850_9","pdf_url":"https://link.springer.com/content/pdf/10.1007/11890850_9.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"book-chapter","type_crossref":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/11890850_9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113501964","display_name":"Tara D. Talbott","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara D. Talbott","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA#TAB#"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA#TAB#","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007415260","display_name":"Karen Schuchardt","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen L. Schuchardt","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA#TAB#"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA#TAB#","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054903654","display_name":"Eric Stephan","orcid":"https://orcid.org/0000-0002-8155-6806"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric G. Stephan","raw_affiliation_strings":["Pacific Northwest National Laboratory, Richland, WA#TAB#"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, Richland, WA#TAB#","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081811890","display_name":"James D. Myers","orcid":"https://orcid.org/0000-0001-8462-650X"},"institutions":[{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James D. Myers","raw_affiliation_strings":["National Center for Supercomputing Applications, Urbana, IL"],"affiliations":[{"raw_affiliation_string":"National Center for Supercomputing Applications, Urbana, IL","institution_ids":["https://openalex.org/I4210135837"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392,"provenance":"doaj"},"apc_paid":null,"fwci":1.393,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":7,"citation_normalized_percentile":{"value":0.716126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":79,"max":80},"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"81"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontology Development","score":0.9987,"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 Ontology Development","score":0.9987,"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/T11986","display_name":"Management and Reproducibility of Scientific Workflows","score":0.998,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T10317","display_name":"Data Stream Management Systems and Techniques","score":0.9967,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/xml","display_name":"XML","score":0.562466},{"id":"https://openalex.org/keywords/description-logics","display_name":"Description Logics","score":0.543204},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema Matching","score":0.539678},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data Integration","score":0.516656},{"id":"https://openalex.org/keywords/logical-data-model","display_name":"Logical data model","score":0.50854623},{"id":"https://openalex.org/keywords/linked-data","display_name":"Linked Data","score":0.502974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9158988},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.77224547},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.77055234},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.57783526},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.55097336},{"id":"https://openalex.org/C203702819","wikidata":"https://www.wikidata.org/wiki/Q17146953","display_name":"Logical data model","level":3,"score":0.50854623},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.50646675},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.50418293},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4353953},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3212067},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30952471},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.30830818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2528677},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/11890850_9","pdf_url":"https://link.springer.com/content/pdf/10.1007/11890850_9.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1007/11890850_9","pdf_url":"https://link.springer.com/content/pdf/10.1007/11890850_9.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319965","https://openalex.org/P4310319900"],"host_organization_lineage_names":["Springer Nature","Springer Science+Business Media"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":5,"referenced_works":["https://openalex.org/W1964126011","https://openalex.org/W2049727745","https://openalex.org/W2075203604","https://openalex.org/W4232837932","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W846443833","https://openalex.org/W81164209","https://openalex.org/W638142098","https://openalex.org/W3089353361","https://openalex.org/W3046984657","https://openalex.org/W2991945580","https://openalex.org/W2098136777","https://openalex.org/W2053943328","https://openalex.org/W2050347474","https://openalex.org/W1592030807"],"abstract_inverted_index":{"Scientists,":[0],"motivated":[1],"by":[2,41,46],"the":[3,53,69,104,108,124,127,133],"desire":[4],"for":[5,67,107],"systems-level":[6],"understanding":[7],"of":[8,71,123,129,137,147],"phenomena,":[9],"increasingly":[10],"need":[11],"to":[12,23,89,141],"share":[13],"their":[14],"results":[15],"across":[16],"multiple":[17],"disciplines.":[18],"Accomplishing":[19],"this":[20,56,138],"requires":[21],"data":[22,76,80,149],"be":[24,39,87],"annotated,":[25],"contextualized,":[26],"and":[27,30,74,92,96,113,131,135,145],"readily":[28],"searchable":[29],"translated":[31],"into":[32],"other":[33],"formats.":[34],"While":[35],"these":[36],"requirements":[37],"can":[38,86],"addressed":[40],"custom":[42],"programming":[43],"or":[44],"obviated":[45],"community":[47],"standardization,":[48],"neither":[49],"approach":[50,62,140],"has":[51],"\u2018solved\u2019":[52],"problem.":[54],"In":[55],"paper,":[57],"we":[58],"describe":[59],"a":[60,64,78],"complementary":[61],"\u2013":[63],"general":[65,139],"capability":[66],"articulating":[68],"format":[70],"arbitrary":[72],"textual":[73],"binary":[75],"using":[77],"logical":[79],"model,":[81],"expressed":[82],"in":[83],"XMLSchema,":[84],"which":[85],"used":[88],"provide":[90],"annotation":[91],"context,":[93],"extract":[94],"metadata,":[95],"enable":[97],"translation.":[98],"This":[99],"work":[100],"is":[101],"based":[102],"on":[103],"draft":[105],"specification":[106],"Data":[109],"Format":[110],"Description":[111],"Language":[112],"our":[114],"open":[115],"source":[116],"\u201cDefuddle\u201d":[117],"parser.":[118],"We":[119],"present":[120],"an":[121],"overview":[122],"specification,":[125],"detail":[126],"design":[128],"Defuddle,":[130],"discuss":[132],"benefits":[134],"challenges":[136],"enabling":[142],"discovery,":[143],"sharing,":[144],"interpretation":[146],"diverse":[148],"sets.":[150]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1603620849","counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2024-11-24T00:50:38.730443","created_date":"2016-06-24"}
