{"id":"https://openalex.org/W2114083529","doi":"https://doi.org/10.3115/v1/d14-1171","title":"Fast and Accurate Misspelling Correction in Large Corpora","display_name":"Fast and Accurate Misspelling Correction in Large Corpora","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2114083529","doi":"https://doi.org/10.3115/v1/d14-1171","mag":"2114083529"},"language":"en","primary_location":{"id":"doi:10.3115/v1/d14-1171","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1171","pdf_url":"https://aclanthology.org/D14-1171.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":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/D14-1171.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034757155","display_name":"Octavian Popescu","orcid":"https://orcid.org/0000-0002-2597-7155"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Octavian Popescu","raw_affiliation_strings":["Fondazione Bruno Kessler Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015531707","display_name":"Ngoc Phuoc An Vo","orcid":"https://orcid.org/0000-0001-5646-5411"},"institutions":[{"id":"https://openalex.org/I33976269","display_name":"Xerox (France)","ror":"https://ror.org/033q0mv79","country_code":"FR","type":"company","lineage":["https://openalex.org/I33976269","https://openalex.org/I4210132870"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ngoc Phuoc An Vo","raw_affiliation_strings":["Xerox (France), Saint-Denis, France"],"affiliations":[{"raw_affiliation_string":"Xerox (France), Saint-Denis, France","institution_ids":["https://openalex.org/I33976269"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034757155"],"corresponding_institution_ids":["https://openalex.org/I2277624104"],"apc_list":null,"apc_paid":null,"fwci":0.8457,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82125641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1634","last_page":"1642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"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":0.695618212223053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.415330708026886},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3996015787124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695618212223053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.415330708026886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3996015787124634}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/d14-1171","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1171","pdf_url":"https://aclanthology.org/D14-1171.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":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.5159","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.5159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://emnlp2014.org/papers/pdf/EMNLP2014171.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.698.2181","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.698.2181","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D14/D14-1171.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/d14-1171","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1171","pdf_url":"https://aclanthology.org/D14-1171.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":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2114083529.pdf","grobid_xml":"https://content.openalex.org/works/W2114083529.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W269399209","https://openalex.org/W1554944419","https://openalex.org/W1650656906","https://openalex.org/W1682095442","https://openalex.org/W1984514442","https://openalex.org/W1988560194","https://openalex.org/W2001496424","https://openalex.org/W2054899689","https://openalex.org/W2066792529","https://openalex.org/W2116061846","https://openalex.org/W2117084652","https://openalex.org/W2118445761","https://openalex.org/W2119224635","https://openalex.org/W2131345120","https://openalex.org/W2138245871","https://openalex.org/W2148474294","https://openalex.org/W2164555064","https://openalex.org/W2729906263","https://openalex.org/W2760279167","https://openalex.org/W4320013820"],"related_works":["https://openalex.org/W2899084033","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/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W3192589309"],"abstract_inverted_index":{"There":[0],"are":[1],"several":[2],"NLP":[3],"systems":[4],"whose":[5],"accuracy":[6],"depends":[7],"crucially":[8],"on":[9,19],"finding":[10],"misspellings":[11],"fast.":[12],"However,":[13],"the":[14,42,72,75],"classical":[15],"approach":[16],"is":[17],"based":[18],"a":[20,29,54],"quadratic":[21],"time":[22,39],"algorithm":[23,31,51],"with":[24,53],"80%":[25],"coverage.":[26],"We":[27,48],"present":[28],"novel":[30],"for":[32],"misspelling":[33],"detection,":[34],"which":[35],"runs":[36],"in":[37,59],"constant":[38],"and":[40],"improves":[41],"coverage":[43],"to":[44,61],"more":[45],"than":[46],"96%.":[47],"use":[49],"this":[50],"together":[52],"cross":[55],"document":[56],"coreference":[57],"system":[58],"order":[60],"find":[62],"proper":[63],"name":[64],"misspellings.":[65],"The":[66],"experiments":[67],"confirmed":[68],"significant":[69],"improvement":[70],"over":[71],"state":[73],"of":[74],"art.":[76]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}