{"id":"https://openalex.org/W2999379159","doi":"https://doi.org/10.1109/iccp48234.2019.8959636","title":"A New Challenge in the Data Processing of Non-Standard Texts Containing Accents / Diacritics: A Case Study","display_name":"A New Challenge in the Data Processing of Non-Standard Texts Containing Accents / Diacritics: A Case Study","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2999379159","doi":"https://doi.org/10.1109/iccp48234.2019.8959636","mag":"2999379159"},"language":"en","primary_location":{"id":"doi:10.1109/iccp48234.2019.8959636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp48234.2019.8959636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP)","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/A5049922385","display_name":"Veronica Gavrila","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114681","display_name":"National Institute for Research & Development in Informatics","ror":"https://ror.org/028rq5v79","country_code":"RO","type":"facility","lineage":["https://openalex.org/I4210114681"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Veronica Gavril\u0103","raw_affiliation_strings":["National Institute of Research and Development in Informatics,Bucharest,Romania","National Institute of Research and Development in Informatics, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"National Institute of Research and Development in Informatics,Bucharest,Romania","institution_ids":["https://openalex.org/I4210114681"]},{"raw_affiliation_string":"National Institute of Research and Development in Informatics, Bucharest, Romania","institution_ids":["https://openalex.org/I4210114681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085603040","display_name":"Lidia B\u00e3jenaru","orcid":"https://orcid.org/0000-0002-1800-3897"},"institutions":[{"id":"https://openalex.org/I4210114681","display_name":"National Institute for Research & Development in Informatics","ror":"https://ror.org/028rq5v79","country_code":"RO","type":"facility","lineage":["https://openalex.org/I4210114681"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Lidia B\u0103jenaru","raw_affiliation_strings":["National Institute of Research and Development in Informatics,Bucharest,Romania","National Institute of Research and Development in Informatics, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"National Institute of Research and Development in Informatics,Bucharest,Romania","institution_ids":["https://openalex.org/I4210114681"]},{"raw_affiliation_string":"National Institute of Research and Development in Informatics, Bucharest, Romania","institution_ids":["https://openalex.org/I4210114681"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024776367","display_name":"Ciprian Dobre","orcid":"https://orcid.org/0000-0003-4638-7725"},"institutions":[{"id":"https://openalex.org/I4210114681","display_name":"National Institute for Research & Development in Informatics","ror":"https://ror.org/028rq5v79","country_code":"RO","type":"facility","lineage":["https://openalex.org/I4210114681"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Ciprian Dobre","raw_affiliation_strings":["National Institute of Research and Development in Informatics,Bucharest,Romania","National Institute of Research and Development in Informatics, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"National Institute of Research and Development in Informatics,Bucharest,Romania","institution_ids":["https://openalex.org/I4210114681"]},{"raw_affiliation_string":"National Institute of Research and Development in Informatics, Bucharest, Romania","institution_ids":["https://openalex.org/I4210114681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049922385"],"corresponding_institution_ids":["https://openalex.org/I4210114681"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17915453,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.7918999791145325,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.7918999791145325,"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":0.7182999849319458,"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/unicode","display_name":"Unicode","score":0.9799728393554688},{"id":"https://openalex.org/keywords/romanian","display_name":"Romanian","score":0.8992539048194885},{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.8084553480148315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7780649065971375},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6088107824325562},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5285844802856445},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4577007591724396},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4328742027282715},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41645222902297974},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34644025564193726},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3004871606826782},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1891239881515503},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17662224173545837},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.0835583508014679},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.0834932029247284}],"concepts":[{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.9799728393554688},{"id":"https://openalex.org/C129400051","wikidata":"https://www.wikidata.org/wiki/Q7913","display_name":"Romanian","level":2,"score":0.8992539048194885},{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.8084553480148315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780649065971375},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6088107824325562},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5285844802856445},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4577007591724396},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4328742027282715},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41645222902297974},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34644025564193726},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3004871606826782},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1891239881515503},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17662224173545837},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0835583508014679},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0834932029247284},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccp48234.2019.8959636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp48234.2019.8959636","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 15th International Conference on Intelligent Computer Communication and Processing (ICCP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2955534458","https://openalex.org/W3043907376","https://openalex.org/W6737429235"],"related_works":["https://openalex.org/W1858249912","https://openalex.org/W1953677193","https://openalex.org/W2114034199","https://openalex.org/W4391249598","https://openalex.org/W2317428717","https://openalex.org/W2734259032","https://openalex.org/W3094038556","https://openalex.org/W2014772881","https://openalex.org/W3113362864","https://openalex.org/W4254228154"],"abstract_inverted_index":{"The":[0,12],"INTELLIT":[1],"project":[2],"develops":[3],"a":[4],"virtual":[5],"online":[6],"museum":[7],"of":[8,14,28,32,41,53,72],"the":[9,21,33,38,54,87,114,118],"Romanian":[10,22,29,34,42],"literature.":[11],"sources":[13],"data":[15],"made":[16],"available":[17],"and":[18,37,46,63,75,108],"provided":[19],"by":[20],"Academy,":[23],"such":[24],"as:":[25],"General":[26],"Dictionary":[27],"Literature,":[30],"Timeline":[31],"Literary":[35],"Life":[36],"canonical":[39],"works":[40],"writers":[43],"are":[44],"digitized":[45],"indexed":[47],"using":[48],"smart":[49],"text":[50,83,98],"analytics.":[51],"One":[52],"challenges":[55],"with":[56,61],"this":[57],"process":[58],"is":[59],"dealing":[60],"diacritics":[62],"textual":[64],"accents.":[65],"Here,":[66],"we":[67],"present":[68,86],"an":[69,91],"in-depth":[70],"analysis":[71],"possible":[73],"solutions":[74],"describe":[76],"our":[77,106],"implementation":[78],"for":[79],"detecting":[80],"various":[81],"Unicode":[82,97],"processing.":[84],"We":[85],"solution":[88],"identified":[89],"as":[90],"accessible":[92],"way":[93],"to":[94,103],"remove":[95],"specific":[96],"code":[99],"points":[100],"in":[101],"order":[102],"greatly":[104],"improve":[105],"search":[107],"filtering":[109],"capabilities":[110],"while":[111],"still":[112],"preserving":[113],"original":[115],"source":[116],"(at":[117],"database":[119],"level).":[120]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
