{"id":"https://openalex.org/W2075196455","doi":"https://doi.org/10.15439/2014f406","title":"Data Cleansing of the Fire &amp; Rescue Text Corpus. The Case Study of Correction of the Misspellings and Segmentation into Sentences.","display_name":"Data Cleansing of the Fire &amp; Rescue Text Corpus. The Case Study of Correction of the Misspellings and Segmentation into Sentences.","publication_year":2014,"publication_date":"2014-09-29","ids":{"openalex":"https://openalex.org/W2075196455","doi":"https://doi.org/10.15439/2014f406","mag":"2075196455"},"language":"en","primary_location":{"id":"doi:10.15439/2014f406","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2014f406","pdf_url":"https://annals-csis.org/proceedings/2014/pliks/406.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://annals-csis.org/proceedings/2014/pliks/406.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052676298","display_name":"Karol Kre\u0144ski","orcid":"https://orcid.org/0000-0001-8595-2913"},"institutions":[{"id":"https://openalex.org/I4210139254","display_name":"Main School of Fire Service","ror":"https://ror.org/03s53tn92","country_code":"PL","type":"education","lineage":["https://openalex.org/I4210139254"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Karol Kre\u0144ski","raw_affiliation_strings":["Section of Computer Science, The Main School of Fire Service, ul. S\u0142owackiego 52/54, 01-629 Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Section of Computer Science, The Main School of Fire Service, ul. S\u0142owackiego 52/54, 01-629 Warsaw, Poland","institution_ids":["https://openalex.org/I4210139254"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039721168","display_name":"Mateusz Fliszkiewicz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139254","display_name":"Main School of Fire Service","ror":"https://ror.org/03s53tn92","country_code":"PL","type":"education","lineage":["https://openalex.org/I4210139254"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Mateusz Fliszkiewicz","raw_affiliation_strings":["Section of Computer Science, The Main School of Fire Service ul. Sowackiego 52/54, 01-629 Warsaw, Poland","Section of Computer Science, The Main School of Fire Service, ul. S\u0142owackiego 52/54, 01-629 Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Section of Computer Science, The Main School of Fire Service ul. Sowackiego 52/54, 01-629 Warsaw, Poland","institution_ids":["https://openalex.org/I4210139254"]},{"raw_affiliation_string":"Section of Computer Science, The Main School of Fire Service, ul. S\u0142owackiego 52/54, 01-629 Warsaw, Poland","institution_ids":["https://openalex.org/I4210139254"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052676298"],"corresponding_institution_ids":["https://openalex.org/I4210139254"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09259259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"331","last_page":"335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.9771000146865845,"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/T10028","display_name":"Topic Modeling","score":0.9750000238418579,"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":0.7811009287834167},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7390453815460205},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.683214545249939},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.66070556640625},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6514507532119751},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5137618780136108},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5050473809242249},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.4597293436527252},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.4104553461074829},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.2651079297065735},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05757442116737366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811009287834167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7390453815460205},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.683214545249939},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.66070556640625},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6514507532119751},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5137618780136108},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5050473809242249},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.4597293436527252},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.4104553461074829},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.2651079297065735},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05757442116737366},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.15439/2014f406","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2014f406","pdf_url":"https://annals-csis.org/proceedings/2014/pliks/406.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:doaj.org/article:a172399ab5b7485c8b68c54f397f9986","is_oa":false,"landing_page_url":"https://doaj.org/article/a172399ab5b7485c8b68c54f397f9986","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annals of computer science and information systems, Vol 2, Pp 331-335 (2014)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.15439/2014f406","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2014f406","pdf_url":"https://annals-csis.org/proceedings/2014/pliks/406.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335039","display_name":"Narodowe Centrum Bada\u0144 i Rozwoju","ror":"https://ror.org/05pwfyy15"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2075196455.pdf","grobid_xml":"https://content.openalex.org/works/W2075196455.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W189174634","https://openalex.org/W1591694210","https://openalex.org/W1612155886","https://openalex.org/W1647671624","https://openalex.org/W1835250353","https://openalex.org/W2037959956","https://openalex.org/W2059844909","https://openalex.org/W2131576956","https://openalex.org/W2144118087","https://openalex.org/W4301031423","https://openalex.org/W6607809444","https://openalex.org/W6679233156"],"related_works":["https://openalex.org/W2592395359","https://openalex.org/W2535231171","https://openalex.org/W2045342254","https://openalex.org/W1501331687","https://openalex.org/W2326647871","https://openalex.org/W4205247302","https://openalex.org/W2468652214","https://openalex.org/W2501551404","https://openalex.org/W2130144716","https://openalex.org/W1504527458"],"abstract_inverted_index":{"The":[0],"article":[1],"presents":[2],"a":[3],"case":[4],"study":[5,31],"of":[6,22,26,42,51],"applying":[7],"data":[8],"cleansing":[9],"methods":[10],"and":[11,18,36],"segmentation":[12],"procedures":[13],"in":[14,39],"order":[15],"to":[16],"correct":[17],"enhance":[19],"the":[20,23,30,37,40,44,49,53],"structure":[21],"domain":[24],"corpus":[25,54],"fire":[27],"service.":[28],"During":[29],"we":[32],"present":[33],"our":[34],"approach":[35],"results":[38],"task":[41],"correcting":[43],"misspellings,":[45],"as":[46,48],"well":[47],"method":[50],"segmenting":[52],"into":[55],"sentences.":[56]},"counts_by_year":[],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2016-06-24T00:00:00"}
