{"id":"https://openalex.org/W2074258494","doi":"https://doi.org/10.3115/1119149.1119166","title":"Corpora and data preparation for information extraction","display_name":"Corpora and data preparation for information extraction","publication_year":1993,"publication_date":"1993-01-01","ids":{"openalex":"https://openalex.org/W2074258494","doi":"https://doi.org/10.3115/1119149.1119166","mag":"2074258494"},"language":"en","primary_location":{"id":"doi:10.3115/1119149.1119166","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119149.1119166","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119149.1119166","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of a workshop on held at Fredericksburg, Virginia September 19-23, 1993 -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1119149.1119166","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029490430","display_name":"Lynn Carlson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lynn Carlson","raw_affiliation_strings":["Ft. Meade, MD","Ft. Meade, MD#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ft. Meade, MD","institution_ids":[]},{"raw_affiliation_string":"Ft. Meade, MD#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083981773","display_name":"Boyan Onyshkevych","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyan Onyshkevych","raw_affiliation_strings":["Ft. Meade, MD","Ft. Meade, MD#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ft. Meade, MD","institution_ids":[]},{"raw_affiliation_string":"Ft. Meade, MD#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007297992","display_name":"Mary Ellen Okurowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mary Ellen Okurowski","raw_affiliation_strings":["Ft. Meade, MD","Ft. Meade, MD#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ft. Meade, MD","institution_ids":[]},{"raw_affiliation_string":"Ft. Meade, MD#TAB#","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6403,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75567737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"135","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13681","display_name":"Engineering and Information Technology","score":0.8575999736785889,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T13681","display_name":"Engineering and Information Technology","score":0.8575999736785889,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/computer-science","display_name":"Computer science","score":0.7825988531112671},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7229900360107422},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.62394118309021},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.6132109761238098},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5926997661590576},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.557322084903717},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5051687359809875},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.45627301931381226},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.447776734828949},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41519659757614136},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3221104145050049},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2852996289730072},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.2608568072319031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2328869104385376},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08820030093193054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7825988531112671},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7229900360107422},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.62394118309021},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.6132109761238098},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5926997661590576},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.557322084903717},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5051687359809875},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.45627301931381226},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.447776734828949},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41519659757614136},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3221104145050049},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2852996289730072},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2608568072319031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2328869104385376},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08820030093193054},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/1119149.1119166","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119149.1119166","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119149.1119166","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of a workshop on held at Fredericksburg, Virginia September 19-23, 1993 -","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/1119149.1119166","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1119149.1119166","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1119149.1119166","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of a workshop on held at Fredericksburg, Virginia September 19-23, 1993 -","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2074258494.pdf","grobid_xml":"https://content.openalex.org/works/W2074258494.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2329000834","https://openalex.org/W2165504147"],"abstract_inverted_index":{"The":[0,25],"data":[1,4,44,59,74,144],"selection":[2,30],"and":[3,12,23,31,62,80,84,102,107,120,146],"preparation":[5,32,145],"efforts":[6,33,125,136],"which":[7],"led":[8],"to":[9,28,41,55,60,71,78,86,123],"the":[10,48,88,117,134,138],"TIPSTER":[11,37],"Fifth":[13],"Message":[14],"Understanding":[15],"Conference":[16],"(MUC-5)":[17],"corpora":[18],"involved":[19],"substantial":[20],"effort,":[21],"time":[22],"resources.":[24],"Government":[26,128],"commitment":[27,113],"these":[29,124],"stems":[34],"from":[35,126],"four":[36],"Program":[38],"objectives:":[39],"(1)":[40],"provide":[42,56,72],"training":[43],"that":[45],"would":[46],"promote":[47],"development":[49],"of":[50,100],"information":[51],"extraction":[52],"technology,":[53],"(2)":[54],"accurate":[57],"test":[58],"evaluate":[61],"baseline":[63,73],"system":[64],"performance":[65,77],"in":[66,104],"an":[67],"objective":[68],"manner,":[69],"(3)":[70],"for":[75,140,143,151],"human":[76],"understand":[79],"interpret":[81],"machine":[82],"performance,":[83],"(4)":[85],"support":[87,122],"larger":[89],"Natural":[90],"Language":[91],"Processing":[92],"community":[93],"by":[94],"making":[95],"available":[96],"a":[97],"unique":[98],"set":[99],"texts":[101],"templates":[103],"multiple":[105],"domains":[106],"languages":[108],"under":[109],"ARPA":[110],"support.":[111],"This":[112],"was":[114],"demonstrated":[115],"through":[116,133],"managerial,":[118],"technical,":[119],"administrative":[121],"various":[127],"agencies,":[129],"as":[130,132],"well":[131],"contractual":[135],"with":[137],"Institute":[139],"Defense":[141],"Analyses":[142],"New":[147],"Mexico":[148],"State":[149],"University":[150],"software":[152],"tool":[153],"development.":[154]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
