{"id":"https://openalex.org/W3098968008","doi":"https://doi.org/10.5220/0010188405310537","title":"The Person Index Challenge: Extraction of Persons from Messy, Short Texts","display_name":"The Person Index Challenge: Extraction of Persons from Messy, Short Texts","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3098968008","doi":"https://doi.org/10.5220/0010188405310537","mag":"3098968008"},"language":"en","primary_location":{"id":"doi:10.5220/0010188405310537","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010188405310537","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 13th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0010188405310537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036983942","display_name":"Markus Schr\u00f6der","orcid":"https://orcid.org/0000-0001-8416-0535"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Markus Schr\u00f6der","raw_affiliation_strings":["Computer Science Dept., TU Kaiserslautern, Germany, --- Select a Country ---","Smart Data & Knowledge Services Dept., DFKI GmbH, Kaiserslautern, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Computer Science Dept., TU Kaiserslautern, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I153267046"]},{"raw_affiliation_string":"Smart Data & Knowledge Services Dept., DFKI GmbH, Kaiserslautern, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075097064","display_name":"Christian Jilek","orcid":"https://orcid.org/0000-0002-5926-1673"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Jilek","raw_affiliation_strings":["Computer Science Dept., TU Kaiserslautern, Germany, --- Select a Country ---","Smart Data & Knowledge Services Dept., DFKI GmbH, Kaiserslautern, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Computer Science Dept., TU Kaiserslautern, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I153267046"]},{"raw_affiliation_string":"Smart Data & Knowledge Services Dept., DFKI GmbH, Kaiserslautern, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066116295","display_name":"Michael Schulze","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Schulze","raw_affiliation_strings":["Computer Science Dept., TU Kaiserslautern, Germany, --- Select a Country ---","Smart Data & Knowledge Services Dept., DFKI GmbH, Kaiserslautern, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Computer Science Dept., TU Kaiserslautern, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I153267046"]},{"raw_affiliation_string":"Smart Data & Knowledge Services Dept., DFKI GmbH, Kaiserslautern, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101904182","display_name":"Andreas Dengel","orcid":"https://orcid.org/0000-0002-6100-8255"},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Dengel","raw_affiliation_strings":["Computer Science Dept., TU Kaiserslautern, Germany, --- Select a Country ---","Smart Data & Knowledge Services Dept., DFKI GmbH, Kaiserslautern, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Computer Science Dept., TU Kaiserslautern, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I153267046"]},{"raw_affiliation_string":"Smart Data & Knowledge Services Dept., DFKI GmbH, Kaiserslautern, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036983942"],"corresponding_institution_ids":["https://openalex.org/I153267046","https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":0.358,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60614347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"531","last_page":"537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T11719","display_name":"Data Quality and Management","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9894000291824341,"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/T10028","display_name":"Topic Modeling","score":0.9847999811172485,"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/baseline","display_name":"Baseline (sea)","score":0.7607567310333252},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.7014836668968201},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6999959349632263},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5765633583068848},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.552474856376648},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5401713848114014},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5328954458236694},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.49314969778060913},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.4792380630970001},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.47183161973953247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4381890296936035},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24441412091255188},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2134847640991211},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08911922574043274},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.07421979308128357},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07259342074394226}],"concepts":[{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7607567310333252},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.7014836668968201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6999959349632263},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5765633583068848},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.552474856376648},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5401713848114014},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5328954458236694},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.49314969778060913},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.4792380630970001},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.47183161973953247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4381890296936035},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24441412091255188},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2134847640991211},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08911922574043274},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.07421979308128357},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07259342074394226},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0010188405310537","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010188405310537","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 13th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.07990","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.07990","pdf_url":"https://arxiv.org/pdf/2011.07990","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.5220/0010188405310537","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010188405310537","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 13th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1491611863","https://openalex.org/W1977518804","https://openalex.org/W2012350188","https://openalex.org/W2096413109","https://openalex.org/W2100581574","https://openalex.org/W2114290255","https://openalex.org/W2898256678","https://openalex.org/W3137298232"],"related_works":["https://openalex.org/W2168627904","https://openalex.org/W2386430105","https://openalex.org/W2515552481","https://openalex.org/W156769215","https://openalex.org/W1570348318","https://openalex.org/W2015444353","https://openalex.org/W3013494979","https://openalex.org/W2356521405","https://openalex.org/W4308101915","https://openalex.org/W2383111961"],"abstract_inverted_index":{"When":[0],"persons":[1,40,62],"are":[2,25,30,36,41],"mentioned":[3,42],"in":[4,44,71],"texts":[5,50],"with":[6],"their":[7,23,28,34,103],"first":[8,129],"name,":[9],"last":[10],"name":[11],"and/or":[12],"middle":[13],"names,":[14],"there":[15],"can":[16,51,81],"be":[17,52,65],"a":[18,83,91,95,108,116,128,134],"high":[19],"variation":[20],"which":[21],"of":[22,111,149],"names":[24,29,35,58],"used,":[26],"how":[27,76],"ordered":[31],"and":[32,114,152],"if":[33],"abbreviated.":[37],"If":[38],"multiple":[39],"consecutively":[43],"very":[45],"different":[46],"ways,":[47],"especially":[48],"short":[49,87],"perceived":[53],"as":[54,94],"\"messy\".":[55],"Once":[56],"ambiguous":[57],"occur,":[59],"associations":[60],"to":[61,118,131],"may":[63],"not":[64],"inferred":[66],"correctly.":[67],"Despite":[68],"these":[69],"eventualities,":[70],"this":[72,132],"paper":[73],"we":[74,106,145],"ask":[75],"well":[77],"an":[78],"unsupervised":[79],"algorithm":[80],"build":[82],"person":[84,92],"index":[85,93],"from":[86],"texts.":[88],"We":[89],"define":[90],"structured":[96],"table":[97],"that":[98],"distinctly":[99],"catalogs":[100],"individuals":[101],"by":[102],"names.":[104],"First,":[105],"give":[107,127],"formal":[109],"definition":[110],"the":[112,147,150,159],"problem":[113],"describe":[115],"procedure":[117],"generate":[119],"ground":[120],"truth":[121],"data":[122],"for":[123],"future":[124,157],"evaluations.":[125],"To":[126],"solution":[130],"challenge,":[133],"baseline":[135,151],"approach":[136],"is":[137,162],"implemented.":[138],"By":[139],"using":[140],"our":[141],"proposed":[142],"evaluation":[143],"strategy,":[144],"test":[146],"performance":[148],"suggest":[153],"further":[154],"improvements.":[155],"For":[156],"research":[158],"source":[160],"code":[161],"publicly":[163],"available.":[164]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-11-23T00:00:00"}
