{"id":"https://openalex.org/W2085809856","doi":"https://doi.org/10.1145/2595188.2595191","title":"An approach to unsupervised historical text normalisation","display_name":"An approach to unsupervised historical text normalisation","publication_year":2014,"publication_date":"2014-05-19","ids":{"openalex":"https://openalex.org/W2085809856","doi":"https://doi.org/10.1145/2595188.2595191","mag":"2085809856"},"language":"en","primary_location":{"id":"doi:10.1145/2595188.2595191","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2595188.2595191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-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/A5074708488","display_name":"Petar Mitankin","orcid":null},"institutions":[{"id":"https://openalex.org/I58918642","display_name":"Sofia University \"St. Kliment Ohridski\"","ror":"https://ror.org/02jv3k292","country_code":"BG","type":"education","lineage":["https://openalex.org/I58918642"]}],"countries":["BG"],"is_corresponding":true,"raw_author_name":"Petar Mitankin","raw_affiliation_strings":["FMI, Sofia University, Sofia, Bulgaria","FMI - Sofia University, Sofia, Bulgaria"],"affiliations":[{"raw_affiliation_string":"FMI, Sofia University, Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]},{"raw_affiliation_string":"FMI - Sofia University, Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006721962","display_name":"Stefan Gerdjikov","orcid":"https://orcid.org/0000-0002-5857-0466"},"institutions":[{"id":"https://openalex.org/I58918642","display_name":"Sofia University \"St. Kliment Ohridski\"","ror":"https://ror.org/02jv3k292","country_code":"BG","type":"education","lineage":["https://openalex.org/I58918642"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Stefan Gerdjikov","raw_affiliation_strings":["FMI, Sofia University, Sofia, Bulgaria","FMI - Sofia University, Sofia, Bulgaria"],"affiliations":[{"raw_affiliation_string":"FMI, Sofia University, Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]},{"raw_affiliation_string":"FMI - Sofia University, Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114255303","display_name":"Stoyan Mihov","orcid":null},"institutions":[{"id":"https://openalex.org/I24768866","display_name":"Bulgarian Academy of Sciences","ror":"https://ror.org/01x8hew03","country_code":"BG","type":"funder","lineage":["https://openalex.org/I24768866"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Stoyan Mihov","raw_affiliation_strings":["IICT, Bulgarian Academy of Sciences, Sofia, Bulgaria"],"affiliations":[{"raw_affiliation_string":"IICT, Bulgarian Academy of Sciences, Sofia, Bulgaria","institution_ids":["https://openalex.org/I24768866"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074708488"],"corresponding_institution_ids":["https://openalex.org/I58918642"],"apc_list":null,"apc_paid":null,"fwci":1.227,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85019024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9991000294685364,"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":0.9890999794006348,"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/computer-science","display_name":"Computer science","score":0.6487419605255127},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46077650785446167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45839086174964905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6487419605255127},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46077650785446167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45839086174964905}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2595188.2595191","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2595188.2595191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[{"id":"https://openalex.org/G7422091512","display_name":null,"funder_award_id":"316087","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"},{"id":"https://openalex.org/G8728025917","display_name":null,"funder_award_id":"269973","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338351","display_name":"FP7 Research Potential of Convergence Regions","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W619445499","https://openalex.org/W629021723","https://openalex.org/W1481336878","https://openalex.org/W1524613437","https://openalex.org/W1571842286","https://openalex.org/W1596151138","https://openalex.org/W1597376089","https://openalex.org/W1647671624","https://openalex.org/W1958077162","https://openalex.org/W1989138986","https://openalex.org/W2006969979","https://openalex.org/W2020278455","https://openalex.org/W2030839740","https://openalex.org/W2041138961","https://openalex.org/W2057900969","https://openalex.org/W2059513841","https://openalex.org/W2060380454","https://openalex.org/W2080627698","https://openalex.org/W2097927681","https://openalex.org/W2101105183","https://openalex.org/W2102443632","https://openalex.org/W2108560279","https://openalex.org/W2119168550","https://openalex.org/W2125838338","https://openalex.org/W2133503566","https://openalex.org/W2144226312","https://openalex.org/W2150429754","https://openalex.org/W2158112271","https://openalex.org/W2188604753","https://openalex.org/W2251281355","https://openalex.org/W2251969247","https://openalex.org/W2950186769","https://openalex.org/W4214671568","https://openalex.org/W4299897201"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,29,68,74,87,115],"novel":[3],"approach":[4,11,82],"to":[5],"unsupervised":[6,81,117],"noisy":[7],"text":[8,95],"correction.":[9],"Our":[10],"is":[12,65,83],"based":[13],"on":[14,43],"automatic":[15],"extraction":[16],"of":[17,25,38,79,108],"historical":[18,30,112],"variation":[19,46],"patterns":[20,47],"by":[21],"analysing":[22],"the":[23,26,36,39,44,48,58,62,92],"structure":[24,37],"words":[27],"from":[28],"corpus":[31],"and":[32],"comparing":[33],"it":[34],"with":[35,67,91],"contemporary":[40],"dictionary.":[41,60],"Based":[42],"extracted":[45],"core":[49],"candidate":[50],"generator,":[51],"REBELS,":[52],"produces":[53],"correction":[54,64],"candidates":[55],"even":[56],"outside":[57],"modern":[59,69],"Further,":[61],"sentence":[63],"complemented":[66],"language":[70],"model":[71],"combined":[72],"in":[73,114],"log-linear":[75],"model.":[76],"The":[77,98],"quality":[78],"our":[80,102],"empirically":[84],"compared":[85],"against":[86],"supervised":[88,94],"system":[89,103],"competitive":[90],"state-of-the-art":[93],"normalisation":[96,106],"systems.":[97],"experiments":[99],"show":[100],"that":[101],"delivers":[104],"81.79%":[105],"accuracy":[107],"17th":[109],"century":[110],"English":[111],"texts":[113],"fully":[116],"setup.":[118]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}