{"id":"https://openalex.org/W2034008407","doi":"https://doi.org/10.5220/0005140401810186","title":"Towards Unsupervised Word Error Correction in Textual Big Data","display_name":"Towards Unsupervised Word Error Correction in Textual Big Data","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2034008407","doi":"https://doi.org/10.5220/0005140401810186","mag":"2034008407"},"language":"en","primary_location":{"id":"doi:10.5220/0005140401810186","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005140401810186","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Fuzzy Computation Theory and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0005140401810186","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029618080","display_name":"Jo\u00e3o Paulo Carvalho","orcid":"https://orcid.org/0000-0003-0005-8299"},"institutions":[{"id":"https://openalex.org/I4210105462","display_name":"Lus\u00edada University of Lisbon","ror":"https://ror.org/00zjprf31","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210105462","https://openalex.org/I4401200244"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Joao Paulo Carvalho","raw_affiliation_strings":["Universidade de Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I4210105462","https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070419583","display_name":"S\u00e9rgio Curto","orcid":"https://orcid.org/0000-0002-0988-221X"},"institutions":[{"id":"https://openalex.org/I4210105462","display_name":"Lus\u00edada University of Lisbon","ror":"https://ror.org/00zjprf31","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210105462","https://openalex.org/I4401200244"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"S\u00e9rgio Curto","raw_affiliation_strings":["Universidade de Lisboa, Portugal"],"affiliations":[{"raw_affiliation_string":"Universidade de Lisboa, Portugal","institution_ids":["https://openalex.org/I4210105462","https://openalex.org/I141596103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029618080"],"corresponding_institution_ids":["https://openalex.org/I141596103","https://openalex.org/I4210105462"],"apc_list":null,"apc_paid":null,"fwci":0.409,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73698586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"181","last_page":"186"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9739000201225281,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9739000201225281,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9685999751091003,"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":0.9595999717712402,"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":0.8551732897758484},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7482571005821228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6521159410476685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6229365468025208},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5369002819061279},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4450475871562958},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.43562600016593933},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.42657631635665894},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.25123482942581177},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08984777331352234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8551732897758484},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7482571005821228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6521159410476685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6229365468025208},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5369002819061279},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4450475871562958},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.43562600016593933},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42657631635665894},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25123482942581177},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08984777331352234},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0005140401810186","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005140401810186","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Fuzzy Computation Theory and Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0005140401810186","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0005140401810186","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Fuzzy Computation Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1579838312","https://openalex.org/W1647671624","https://openalex.org/W1978909929","https://openalex.org/W1991296835","https://openalex.org/W2025821008","https://openalex.org/W2066792529","https://openalex.org/W2094054193","https://openalex.org/W2122285802","https://openalex.org/W2122966699","https://openalex.org/W2141658687","https://openalex.org/W2162949830"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W2296205523","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"Large":[0],"unedited":[1],"technical":[2],"textual":[3,116],"databases":[4,99],"might":[5],"contain":[6,52],"information":[7,54],"that":[8,55,73,100],"cannot":[9],"be":[10],"properly":[11],"extracted":[12],"using":[13],"Natural":[14],"Language":[15],"Processing":[16],"(NLP)":[17],"tools":[18],"due":[19],"to":[20,87,114],"the":[21,30,90,103,115],"many":[22],"existent":[23],"word":[24,94],"errors.":[25],"A":[26],"good":[27],"example":[28],"is":[29],"MIMIC":[31],"II":[32],"database,":[33],"where":[34],"medical":[35],"text":[36],"reports":[37,51],"are":[38],"a":[39,82],"direct":[40,104],"representation":[41],"of":[42,93,106,112],"experts\u00e2\u0080\u0099":[43],"views":[44],"on":[45,64],"real":[46],"time":[47],"observable":[48],"data.":[49,117],"Such":[50],"valuable":[53],"can":[56],"improve":[57],"predictive":[58],"medic":[59],"decision":[60],"making":[61],"models":[62],"based":[63,84],"physiological":[65],"data,":[66],"but":[67],"have":[68],"never":[69],"been":[70],"used":[71],"with":[72],"goal":[74],"so":[75],"far.":[76],"In":[77],"this":[78],"paper":[79],"we":[80],"propose":[81],"fuzzy":[83],"semi-automatic":[85],"method":[86],"specifically":[88],"address":[89],"large":[91],"number":[92],"errors":[95],"contained":[96],"in":[97],"such":[98,109],"will":[101],"allow":[102],"application":[105],"NLP":[107],"techniques,":[108],"as":[110],"Bag":[111],"Words,":[113]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}