{"id":"https://openalex.org/W2030012932","doi":"https://doi.org/10.1145/2016039.2016069","title":"Efficient schema extraction from a large collection of XML documents","display_name":"Efficient schema extraction from a large collection of XML documents","publication_year":2011,"publication_date":"2011-03-24","ids":{"openalex":"https://openalex.org/W2030012932","doi":"https://doi.org/10.1145/2016039.2016069","mag":"2030012932"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/2016039.2016069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5019398706","display_name":"Guangming Xing","orcid":"https://orcid.org/0000-0002-1234-5247"},"institutions":[{"id":"https://openalex.org/I94339441","display_name":"Western Kentucky University","ror":"https://ror.org/0446vnd56","country_code":"US","type":"education","lineage":["https://openalex.org/I94339441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guangming Xing","raw_affiliation_strings":["Western Kentucky University, Bowling Green, KY"],"affiliations":[{"raw_affiliation_string":"Western Kentucky University, Bowling Green, KY","institution_ids":["https://openalex.org/I94339441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033117109","display_name":"Vijayeandra Parthepan","orcid":null},"institutions":[{"id":"https://openalex.org/I94339441","display_name":"Western Kentucky University","ror":"https://ror.org/0446vnd56","country_code":"US","type":"education","lineage":["https://openalex.org/I94339441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijayeandra Parthepan","raw_affiliation_strings":["Western Kentucky University, Bowling Green, KY"],"affiliations":[{"raw_affiliation_string":"Western Kentucky University, Bowling Green, KY","institution_ids":["https://openalex.org/I94339441"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.502,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":2,"citation_normalized_percentile":{"value":0.3945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":72,"max":76},"biblio":{"volume":null,"issue":null,"first_page":"92","last_page":"96"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9973,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9929,"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/schema","display_name":"Schema (genetic algorithms)","score":0.64612794},{"id":"https://openalex.org/keywords/xml-schema","display_name":"XML Schema (W3C)","score":0.563148},{"id":"https://openalex.org/keywords/relax-ng","display_name":"RELAX NG","score":0.5470487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79975545},{"id":"https://openalex.org/C34716815","wikidata":"https://www.wikidata.org/wiki/Q8042322","display_name":"XML Schema Editor","level":3,"score":0.789464},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.788918},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.72463113},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.6697531},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.64612794},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.59192824},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.56635886},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.563148},{"id":"https://openalex.org/C44540991","wikidata":"https://www.wikidata.org/wiki/Q1314117","display_name":"RELAX NG","level":5,"score":0.5470487},{"id":"https://openalex.org/C44883583","wikidata":"https://www.wikidata.org/wiki/Q7622687","display_name":"Streaming XML","level":3,"score":0.5258463},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.51197255},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.41346097},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3654273},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.36363786},{"id":"https://openalex.org/C173242113","wikidata":"https://www.wikidata.org/wiki/Q607488","display_name":"XML Encryption","level":4,"score":0.2746885},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2615893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15143162}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/2016039.2016069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":13,"referenced_works":["https://openalex.org/W1489432736","https://openalex.org/W1535992660","https://openalex.org/W1606434866","https://openalex.org/W1664954303","https://openalex.org/W1777938571","https://openalex.org/W1880452510","https://openalex.org/W2040374677","https://openalex.org/W2087613132","https://openalex.org/W2106950427","https://openalex.org/W2116493296","https://openalex.org/W2131968429","https://openalex.org/W2489487449","https://openalex.org/W4248809068"],"related_works":["https://openalex.org/W3215612463","https://openalex.org/W2587776232","https://openalex.org/W2330886247","https://openalex.org/W2170192471","https://openalex.org/W2137809776","https://openalex.org/W2130593017","https://openalex.org/W2075518598","https://openalex.org/W2060533116","https://openalex.org/W2042456137","https://openalex.org/W2016611442"],"abstract_inverted_index":{"XML":[0,31,74],"is":[1,20],"becoming":[2],"the":[3,10,39,47,57,62,65,78],"standard":[4],"format":[5],"for":[6,88],"data":[7,75],"exchange":[8],"on":[9,34,72],"Internet.":[11],"In":[12],"this":[13],"paper,":[14],"we":[15,36],"present":[16],"a":[17,27,86],"system":[18],"that":[19],"effective":[21],"in":[22],"extracting":[23],"schema":[24,66,89],"information":[25],"from":[26],"large":[28],"collection":[29],"of":[30,41,56,64,82],"documents.":[32],"Based":[33],"Xtract,":[35],"propose":[37],"using":[38,54],"cost":[40],"an":[42],"NFA":[43],"simulation":[44],"to":[45,60],"compute":[46],"Minimum":[48],"Length":[49],"Description.":[50],"We":[51],"also":[52],"studied":[53],"frequencies":[55],"sample":[58],"inputs":[59],"improve":[61],"effectiveness":[63,81],"extraction.":[67],"Experimental":[68],"studies":[69],"were":[70],"conducted":[71],"synthesized":[73],"sets,":[76],"suggesting":[77],"efficiency":[79],"and":[80],"our":[83],"approach":[84],"as":[85],"solution":[87],"inference.":[90]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2030012932","counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2024-12-12T04:13:54.902287","created_date":"2016-06-24"}