{"id":"https://openalex.org/W1990682310","doi":"https://doi.org/10.1117/12.2002509","title":"Rule-based versus training-based extraction of index terms from business documents: how to combine the results","display_name":"Rule-based versus training-based extraction of index terms from business documents: how to combine the results","publication_year":2013,"publication_date":"2013-02-04","ids":{"openalex":"https://openalex.org/W1990682310","doi":"https://doi.org/10.1117/12.2002509","mag":"1990682310"},"language":"en","primary_location":{"id":"doi:10.1117/12.2002509","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2002509","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","raw_type":"proceedings-article"},"type":"conference-paper","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/A5061819674","display_name":"Daniel Schuster","orcid":"https://orcid.org/0000-0002-6512-9580"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Schuster","raw_affiliation_strings":["TU Dresden (Germany)","TU-Dresden (Germany)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Dresden (Germany)","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"TU-Dresden (Germany)","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042376015","display_name":"Marcel Hanke","orcid":"https://orcid.org/0000-0002-5024-1684"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marcel Hanke","raw_affiliation_strings":["TU Dresden (Germany)","TU-Dresden (Germany)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Dresden (Germany)","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"TU-Dresden (Germany)","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031734305","display_name":"Klemens Muthmann","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klemens Muthmann","raw_affiliation_strings":["TU Dresden (Germany)","TU-Dresden (Germany)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Dresden (Germany)","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"TU-Dresden (Germany)","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090662617","display_name":"Daniel E. Esser","orcid":"https://orcid.org/0000-0003-0155-821X"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Esser","raw_affiliation_strings":["TU Dresden (Germany)","TU-Dresden (Germany)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Dresden (Germany)","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"TU-Dresden (Germany)","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":0.4581,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58323904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8658","issue":null,"first_page":"865813","last_page":"865813"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9923999905586243,"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 Ontologies","score":0.9923999905586243,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9905999898910522,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9714999794960022,"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/normalization","display_name":"Normalization (sociology)","score":0.8193626403808594},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8108129501342773},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5902716517448425},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5119351148605347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4429600238800049},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4355483949184418},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4251970648765564},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42361125349998474},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4155483841896057},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39539724588394165},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38674989342689514},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33621248602867126},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0839897096157074}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8193626403808594},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8108129501342773},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5902716517448425},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5119351148605347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4429600238800049},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4355483949184418},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4251970648765564},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42361125349998474},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4155483841896057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39539724588394165},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38674989342689514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33621248602867126},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0839897096157074},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.2002509","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2002509","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828","https://openalex.org/W2469820710","https://openalex.org/W4321276295"],"abstract_inverted_index":{"Current":[0],"systems":[1],"for":[2],"automatic":[3],"extraction":[4,75,84],"of":[5,37,69,93],"index":[6],"terms":[7],"from":[8],"business":[9,96],"documents":[10],"either":[11],"take":[12],"a":[13,42,91],"rule-based":[14],"or":[15],"training-based":[16],"approach.":[17],"As":[18],"both":[19,31,38],"approaches":[20],"have":[21],"their":[22],"advantages":[23],"and":[24,50,90],"disadvantages":[25],"it":[26],"seems":[27],"natural":[28],"to":[29,33,65],"combine":[30],"methods":[32,78],"get":[34],"the":[35,46,67],"best":[36],"worlds.":[39],"We":[40],"present":[41],"combination":[43,51],"method":[44],"with":[45,86],"steps":[47],"selection,":[48],"normalization,":[49],"based":[52],"on":[53,81],"comparable":[54],"scores":[55],"produced":[56],"during":[57],"extraction.":[58],"Furthermore,":[59],"novel":[60],"evaluation":[61],"metrics":[62],"are":[63],"developed":[64],"support":[66],"assessment":[68],"each":[70],"step":[71],"in":[72],"an":[73,82],"existing":[74],"system.":[76],"Our":[77],"were":[79],"evaluated":[80],"example":[83],"system":[85],"three":[87],"individual":[88],"extractors":[89],"corpus":[92],"12,000":[94],"scanned":[95],"documents.":[97]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}