{"id":"https://openalex.org/W2741908291","doi":"https://doi.org/10.18653/v1/w17-2317","title":"Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings","display_name":"Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2741908291","doi":"https://doi.org/10.18653/v1/w17-2317","mag":"2741908291"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-2317","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2317","pdf_url":"https://www.aclweb.org/anthology/W17-2317.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioNLP 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-2317.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050103177","display_name":"Pieter Fivez","orcid":"https://orcid.org/0000-0001-8573-5759"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Pieter Fivez","raw_affiliation_strings":["CLiPS, University of Antwerp, Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CLiPS, University of Antwerp, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008576336","display_name":"Simon \u0160uster","orcid":"https://orcid.org/0000-0002-8817-8545"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]},{"id":"https://openalex.org/I4210102047","display_name":"Antwerp University Hospital","ror":"https://ror.org/01hwamj44","country_code":"BE","type":"funder","lineage":["https://openalex.org/I4210102047"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Simon Suster","raw_affiliation_strings":["CLiPS, University of Antwerp, Antwerp, Belgium","Antwerp University Hospital, Edegem, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CLiPS, University of Antwerp, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]},{"raw_affiliation_string":"Antwerp University Hospital, Edegem, Belgium","institution_ids":["https://openalex.org/I4210102047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083411784","display_name":"Walter Daelemans","orcid":"https://orcid.org/0000-0002-9832-7890"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Walter Daelemans","raw_affiliation_strings":["CLiPS, University of Antwerp, Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CLiPS, University of Antwerp, Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5111,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.94264647,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T13629","display_name":"Text Readability and Simplification","score":0.9987000226974487,"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/spelling","display_name":"Spelling","score":0.8555140495300293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.780895471572876},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6766236424446106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6661036610603333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6603533029556274},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6555098295211792},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6148267984390259},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.552775502204895},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.50654137134552},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.484023779630661},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4277172088623047},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.383425772190094},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3165815472602844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11135846376419067},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09858742356300354},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.05896225571632385}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.8555140495300293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.780895471572876},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6766236424446106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6661036610603333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6603533029556274},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6555098295211792},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6148267984390259},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.552775502204895},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.50654137134552},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.484023779630661},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4277172088623047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.383425772190094},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3165815472602844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11135846376419067},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09858742356300354},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05896225571632385},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-2317","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2317","pdf_url":"https://www.aclweb.org/anthology/W17-2317.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioNLP 2017","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-2317","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-2317","pdf_url":"https://www.aclweb.org/anthology/W17-2317.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioNLP 2017","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313460","display_name":"Agentschap Innoveren en Ondernemen","ror":"https://ror.org/032xdry56"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2741908291.pdf","grobid_xml":"https://content.openalex.org/works/W2741908291.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1489596328","https://openalex.org/W1595714231","https://openalex.org/W1614298861","https://openalex.org/W1984291951","https://openalex.org/W2006642610","https://openalex.org/W2101234009","https://openalex.org/W2110453538","https://openalex.org/W2250962271","https://openalex.org/W2251237590","https://openalex.org/W2293452551","https://openalex.org/W2396881363","https://openalex.org/W2401825159","https://openalex.org/W2419826580","https://openalex.org/W2493916176","https://openalex.org/W2740623990","https://openalex.org/W2950577311"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2787311093","https://openalex.org/W155946694","https://openalex.org/W1555968995","https://openalex.org/W4307474317","https://openalex.org/W2057384730","https://openalex.org/W2147879411","https://openalex.org/W2624072012","https://openalex.org/W2008468404"],"abstract_inverted_index":{"We":[0,49],"present":[1],"an":[2,71],"unsupervised":[3],"contextsensitive":[4],"spelling":[5,55,89],"correction":[6,56,90],"method":[7,19],"for":[8],"clinical":[9],"free-text":[10],"that":[11,77],"uses":[12],"word":[13],"and":[14,24,45,65],"character":[15],"n-gram":[16],"embeddings.":[17],"Our":[18,92],"generates":[20],"misspelling":[21,47],"replacement":[22],"candidates":[23],"ranks":[25],"them":[26],"according":[27],"to":[28,84,98],"their":[29],"semantic":[30],"fit,":[31],"by":[32],"calculating":[33],"a":[34,43,59,88,96],"weighted":[35],"cosine":[36],"similarity":[37],"between":[38],"the":[39,46,67,100],"vectorized":[40],"representation":[41],"of":[42,70],"candidate":[44],"context.":[48],"greatly":[50],"outperform":[51],"two":[52],"baseline":[53],"off-the-shelf":[54],"tools":[57],"on":[58],"manually":[60],"annotated":[61,101],"MIMIC-III":[62],"test":[63,102],"set,":[64],"counter":[66],"frequency":[68],"bias":[69],"optimized":[72],"noisy":[73],"channel":[74],"model,":[75],"showing":[76],"neural":[78],"embeddings":[79],"can":[80,104],"be":[81,105],"successfully":[82],"exploited":[83],"include":[85],"context-awareness":[86],"in":[87],"model.":[91],"source":[93],"code,":[94],"including":[95],"script":[97],"extract":[99],"data,":[103],"found":[106],"at":[107],"https://github.com/":[108],"pieterfivez/bionlp2017.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}