{"id":"https://openalex.org/W2096601602","doi":"https://doi.org/10.1093/llc/fql020","title":"Rule-based Search in Text Databases with Nonstandard Orthography","display_name":"Rule-based Search in Text Databases with Nonstandard Orthography","publication_year":2006,"publication_date":"2006-04-12","ids":{"openalex":"https://openalex.org/W2096601602","doi":"https://doi.org/10.1093/llc/fql020","mag":"2096601602"},"language":"en","primary_location":{"id":"doi:10.1093/llc/fql020","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fql020","pdf_url":null,"source":{"id":"https://openalex.org/S84784070","display_name":"Literary and Linguistic Computing","issn_l":"0268-1145","issn":["0268-1145","1477-4615"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Literary and Linguistic Computing","raw_type":"journal-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/A5075167773","display_name":"Thomas Pilz","orcid":null},"institutions":[{"id":"https://openalex.org/I62318514","display_name":"University of Duisburg-Essen","ror":"https://ror.org/04mz5ra38","country_code":"DE","type":"education","lineage":["https://openalex.org/I62318514"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"T. Pilz","raw_affiliation_strings":["Institute of Computer Science and Interactive Systems, University of Duisburg-Essen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Interactive Systems, University of Duisburg-Essen, Germany","institution_ids":["https://openalex.org/I62318514"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075167773"],"corresponding_institution_ids":["https://openalex.org/I62318514"],"apc_list":null,"apc_paid":null,"fwci":5.0845,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95010716,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"2","first_page":"179","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9829999804496765,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9829999804496765,"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/T12373","display_name":"Linguistic research and analysis","score":0.97079998254776,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13959","display_name":"Swearing, Euphemism, Multilingualism","score":0.9291999936103821,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/orthography","display_name":"Orthography","score":0.7634546756744385},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.7553691864013672},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.704045295715332},{"id":"https://openalex.org/keywords/levenshtein-distance","display_name":"Levenshtein distance","score":0.6949101686477661},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5430253744125366},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5048442482948303},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.4789074659347534},{"id":"https://openalex.org/keywords/ninth","display_name":"Ninth","score":0.45939916372299194},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4574418067932129},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4502626061439514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3688001036643982},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11633554100990295}],"concepts":[{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.7634546756744385},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7553691864013672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.704045295715332},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.6949101686477661},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5430253744125366},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5048442482948303},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.4789074659347534},{"id":"https://openalex.org/C2776244770","wikidata":"https://www.wikidata.org/wiki/Q253590","display_name":"Ninth","level":2,"score":0.45939916372299194},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4574418067932129},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4502626061439514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3688001036643982},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11633554100990295},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/llc/fql020","is_oa":false,"landing_page_url":"https://doi.org/10.1093/llc/fql020","pdf_url":null,"source":{"id":"https://openalex.org/S84784070","display_name":"Literary and Linguistic Computing","issn_l":"0268-1145","issn":["0268-1145","1477-4615"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Literary and Linguistic Computing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.910.1991","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.910.1991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://llc.oxfordjournals.org/content/21/2/179.full.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320325052","display_name":"Universit\u00e4t Duisburg-Essen","ror":"https://ror.org/04mz5ra38"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2890906110","https://openalex.org/W1990552177","https://openalex.org/W2060353616","https://openalex.org/W2356780436","https://openalex.org/W577749800","https://openalex.org/W2554229954","https://openalex.org/W3161898580","https://openalex.org/W2335508101","https://openalex.org/W2899266101","https://openalex.org/W118738503"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3],"describe":[4],"our":[5],"interdisciplinary":[6],"project":[7,115],"\u2018Rule-based":[8],"search":[9,39],"in":[10,17],"text":[11,46],"databases":[12],"with":[13,81,111,132],"nonstandard":[14],"orthography":[15],"(RSNSR)\u2019":[16],"support":[18],"of":[19,22,30,49,126],"the":[20,27,31,112,129,135,142],"conservation":[21],"cultural":[23],"heritage,":[24],"especially":[25],"for":[26,73,128],"German":[28,127],"reception":[29],"philosopher":[32],"Nietzsche.":[33],"We":[34],"present":[35,83,143],"a":[36,102,122],"rule-based":[37],"fuzzy":[38],"engine":[40],"that":[41],"allows":[42],"users":[43],"to":[44,120,141],"retrieve":[45],"data":[47],"independently":[48],"its":[50,82],"orthographical":[51],"realization.":[52],"The":[53],"rules":[54],"used":[55],"are":[56,87,93],"derived":[57],"from":[58,134],"statistical":[59],"analyses,":[60],"historical":[61],"publications,":[62],"linguistic":[63],"principles,":[64],"and":[65,97],"expert":[66],"knowledge.":[67],"Our":[68,107],"Web-based":[69],"tool":[70],"is":[71,109],"intended":[72],"experts":[74],"as":[75,77],"well":[76],"interested":[78],"amateurs.":[79],"Along":[80],"features,":[84],"further":[85],"functions":[86],"currently":[88],"worked":[89],"out.":[90],"Among":[91],"them":[92],"automatic":[94],"rule":[95],"derivation":[96],"finer":[98],"result":[99],"classification":[100],"through":[101],"generalized":[103],"Levenshtein":[104],"similarity":[105],"measure.":[106],"work":[108],"associated":[110],"recently":[113],"launched":[114],"Deutsch":[116],"Diachron":[117],"Digital":[118],"(DDD)":[119],"build":[121],"complete":[123],"diachronic":[124],"corpus":[125],"first":[130],"time":[131],"texts":[133],"ninth":[136],"century":[137],"(Old":[138],"High":[139],"German)":[140],"(Modern":[144],"German).":[145]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
