{"id":"https://openalex.org/W1977706345","doi":"https://doi.org/10.1145/1851476.1851526","title":"ParaText","display_name":"ParaText","publication_year":2010,"publication_date":"2010-06-21","ids":{"openalex":"https://openalex.org/W1977706345","doi":"https://doi.org/10.1145/1851476.1851526","mag":"1977706345"},"language":"en","primary_location":{"id":"doi:10.1145/1851476.1851526","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1851476.1851526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing","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/A5048468459","display_name":"Daniel Dunlavy","orcid":"https://orcid.org/0009-0003-2299-4798"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel M. Dunlavy","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063003315","display_name":"Timothy M. Shead","orcid":"https://orcid.org/0009-0009-5789-9524"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy M. Shead","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069939821","display_name":"Eric Stanton","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric T. Stanton","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM","institution_ids":["https://openalex.org/I4210104735"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8638,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91998234,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"344","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9962000250816345,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9962000250816345,"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":"Advanced Database Systems and Queries","score":0.994700014591217,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9919999837875366,"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/paratext","display_name":"Paratext","score":0.8027272820472717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8019835352897644},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5123792886734009},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.4695485234260559},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4599190950393677},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45285844802856445},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4343310296535492},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.4256259799003601},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4125481843948364},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.2793782353401184},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18096023797988892},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.17132258415222168},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.15659135580062866}],"concepts":[{"id":"https://openalex.org/C2777688565","wikidata":"https://www.wikidata.org/wiki/Q853520","display_name":"Paratext","level":2,"score":0.8027272820472717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019835352897644},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5123792886734009},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.4695485234260559},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4599190950393677},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45285844802856445},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4343310296535492},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.4256259799003601},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4125481843948364},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2793782353401184},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18096023797988892},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.17132258415222168},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15659135580062866},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1851476.1851526","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1851476.1851526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G6871450401","display_name":null,"funder_award_id":"DE-AC04-94AL85000","funder_id":"https://openalex.org/F4320337547","funder_display_name":"Laboratory Directed Research and Development"}],"funders":[{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320337547","display_name":"Laboratory Directed Research and Development","ror":"https://ror.org/01e41cf67"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W32791291","https://openalex.org/W204849900","https://openalex.org/W1557757161","https://openalex.org/W1978849840","https://openalex.org/W1995525279","https://openalex.org/W2001291669","https://openalex.org/W2058616517","https://openalex.org/W2063535907","https://openalex.org/W2086666883","https://openalex.org/W2125046840","https://openalex.org/W2135564618","https://openalex.org/W2918095495"],"related_works":["https://openalex.org/W2089958144","https://openalex.org/W2792305417","https://openalex.org/W3210470316","https://openalex.org/W4389578080","https://openalex.org/W2600483492","https://openalex.org/W2339284686","https://openalex.org/W130815504","https://openalex.org/W4385795891","https://openalex.org/W2602957669","https://openalex.org/W3130974824"],"abstract_inverted_index":{"Automated":[0],"analysis":[1,54,68],"of":[2,55,81,92,103,108],"unstructured":[3,82],"text":[4,56,67,83,109],"documents":[5],"(e.g.,":[6],"web":[7],"pages,":[8],"newswire":[9],"articles,":[10],"research":[11,36],"publications,":[12],"business":[13],"reports)":[14],"is":[15],"a":[16,70],"key":[17],"capability":[18],"for":[19,75],"solving":[20],"important":[21],"problems":[22],"in":[23,46],"areas":[24],"including":[25],"decision":[26],"making,":[27],"risk":[28],"assessment,":[29],"social":[30],"network":[31],"analysis,":[32,34],"intelligence":[33],"scholarly":[35],"and":[37,52,78,101],"others.":[38],"However,":[39],"as":[40],"data":[41,113],"sizes":[42],"continue":[43],"to":[44,96,115],"grow":[45],"these":[47],"areas,":[48],"scalable":[49],"processing,":[50,76],"modeling,":[51,77],"semantic":[53],"collections":[57,80,89],"becomes":[58],"essential.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"present":[64],"the":[65,98,104,105],"ParaText":[66],"engine,":[69],"distributed":[71],"memory":[72],"software":[73],"framework":[74],"analyzing":[79],"documents.":[84],"Results":[85],"on":[86],"several":[87],"document":[88],"using":[90],"hundreds":[91],"processors":[93],"are":[94],"presented":[95],"illustrate":[97],"flexibility,":[99],"extensibility,":[100],"scalability":[102],"entire":[106],"process":[107],"modeling":[110],"from":[111],"raw":[112],"ingestion":[114],"application":[116],"analysis.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}
