{"id":"https://openalex.org/W1974533997","doi":"https://doi.org/10.1145/1255175.1255242","title":"Retrieval in text collections with historic spelling using linguistic and spelling variants","display_name":"Retrieval in text collections with historic spelling using linguistic and spelling variants","publication_year":2007,"publication_date":"2007-06-18","ids":{"openalex":"https://openalex.org/W1974533997","doi":"https://doi.org/10.1145/1255175.1255242","mag":"1974533997"},"language":"en","primary_location":{"id":"doi:10.1145/1255175.1255242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1255175.1255242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries","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/A5050360148","display_name":"Andrea Ernst-Gerlach","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":false,"raw_author_name":"Andrea Ernst-Gerlach","raw_affiliation_strings":["University of Duisburg-Essen, Duisburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Duisburg-Essen, Duisburg, Germany","institution_ids":["https://openalex.org/I62318514"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054035663","display_name":"Norbert Fuhr","orcid":"https://orcid.org/0000-0002-0441-6949"},"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":false,"raw_author_name":"Norbert Fuhr","raw_affiliation_strings":["University of Duisburg-Essen, Duisburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Duisburg-Essen, Duisburg, Germany","institution_ids":["https://openalex.org/I62318514"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62318514"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"333","last_page":"341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12353","display_name":"Lexicography and Language Studies","score":0.9722999930381775,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.964657723903656},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.8267961740493774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7504016160964966},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6936594247817993},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6714890599250793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6208270788192749},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5257450342178345},{"id":"https://openalex.org/keywords/writing-system","display_name":"Writing system","score":0.48723283410072327},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45756417512893677},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4367714822292328},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.43035706877708435}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.964657723903656},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.8267961740493774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504016160964966},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6936594247817993},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6714890599250793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6208270788192749},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5257450342178345},{"id":"https://openalex.org/C78148190","wikidata":"https://www.wikidata.org/wiki/Q8192","display_name":"Writing system","level":2,"score":0.48723283410072327},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45756417512893677},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4367714822292328},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.43035706877708435},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1255175.1255242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1255175.1255242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W86295857","https://openalex.org/W105720630","https://openalex.org/W199687585","https://openalex.org/W335544475","https://openalex.org/W587183953","https://openalex.org/W1481824047","https://openalex.org/W1490022694","https://openalex.org/W1499897207","https://openalex.org/W1555414055","https://openalex.org/W1581712682","https://openalex.org/W1882181510","https://openalex.org/W1978515644","https://openalex.org/W2050050080","https://openalex.org/W2087447526","https://openalex.org/W2110817274","https://openalex.org/W2137416755","https://openalex.org/W2149179161"],"related_works":["https://openalex.org/W2161008081","https://openalex.org/W2100947578","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W4250167163","https://openalex.org/W4220791298"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,40,47],"new":[3],"approach":[4],"for":[5,16,52,71,96],"the":[6,29,60,77,81,93],"retrieval":[7,83,94],"of":[8,32,49,59],"texts":[9,18],"with":[10],"non-standard":[11],"spelling,":[12],"which":[13],"is":[14],"important":[15],"historic":[17,73,97],"e.g.":[19],"in":[20],"English":[21],"or":[22],"German.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27,45,63,79,90],"describe":[28],"overall":[30],"architecture":[31],"our":[33],"system,":[34],"followed":[35],"by":[36],"its":[37],"evaluation.":[38],"Given":[39],"search":[41],"term":[42],"as":[43],"lemma,":[44],"use":[46],"dictionary":[48],"contemporary":[50],"German":[51],"finding":[53],"all":[54],"inflected":[55],"and":[56],"derived":[57],"forms":[58],"lemma.":[61],"Then":[62],"apply":[64],"transformation":[65],"rules":[66],"(derived":[67],"from":[68],"training":[69],"data)":[70],"generating":[72],"spelling":[74],"variants.":[75],"For":[76],"evaluation,":[78],"regard":[80],"resulting":[82],"quality.":[84],"The":[85],"experimental":[86],"results":[87],"show":[88],"that":[89],"can":[91],"improve":[92],"quality":[95],"collections":[98],"substantially.":[99]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
