{"id":"https://openalex.org/W2948335087","doi":"https://doi.org/10.18653/v1/w19-4427","title":"Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data","display_name":"Neural Grammatical Error Correction Systems with Unsupervised Pre-training on Synthetic Data","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2948335087","doi":"https://doi.org/10.18653/v1/w19-4427","mag":"2948335087"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4427","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4427","pdf_url":"https://www.aclweb.org/anthology/W19-4427.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 Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4427.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023392498","display_name":"Roman Grundkiewicz","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roman Grundkiewicz","raw_affiliation_strings":["University of Edinburgh, Scotland, EU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Scotland, EU","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065193578","display_name":"Marcin Junczys-Dowmunt","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcin Junczys-Dowmunt","raw_affiliation_strings":["Microsoft, Redmond, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070589644","display_name":"Kenneth Heafield","orcid":"https://orcid.org/0000-0002-6344-9927"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kenneth Heafield","raw_affiliation_strings":["University of Edinburgh, Scotland, EU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Scotland, EU","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":185,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"263"},"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":0.9994000196456909,"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":0.9889000058174133,"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":0.8454387784004211},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.6590780019760132},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6430907249450684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.595563530921936},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5273771286010742},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.5093036890029907},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.49230825901031494},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4709148108959198},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.469072550535202},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4593425691127777},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4535282254219055},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.44212600588798523},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3594300150871277},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.356453001499176},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3377026915550232},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21615192294120789},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07699644565582275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8454387784004211},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6590780019760132},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6430907249450684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.595563530921936},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5273771286010742},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.5093036890029907},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.49230825901031494},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4709148108959198},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.469072550535202},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4593425691127777},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4535282254219055},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.44212600588798523},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3594300150871277},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.356453001499176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3377026915550232},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21615192294120789},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07699644565582275},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w19-4427","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4427","pdf_url":"https://www.aclweb.org/anthology/W19-4427.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 Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f4751308-f4f8-4116-9204-9c3aa4a37722","is_oa":true,"landing_page_url":"https://www.aclweb.org/anthology/W19-44","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4427","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4427","pdf_url":"https://www.aclweb.org/anthology/W19-4427.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 Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2465893628","display_name":"Peta-5: A National Facility for Petascale Data Intensive Computation and Analytics","funder_award_id":"EP/P020259/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5258663329","display_name":null,"funder_award_id":"EP/P020259/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6661763476","display_name":null,"funder_award_id":"EP/P020259/1","funder_id":"https://openalex.org/F4320320273","funder_display_name":"University of Cambridge"}],"funders":[{"id":"https://openalex.org/F4320312927","display_name":"Dell EMC","ror":"https://ror.org/05rejmm18"},{"id":"https://openalex.org/F4320320273","display_name":"University of Cambridge","ror":"https://ror.org/013meh722"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334632","display_name":"Science and Technology Facilities Council","ror":"https://ror.org/057g20z61"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948335087.pdf","grobid_xml":"https://content.openalex.org/works/W2948335087.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W43022990","https://openalex.org/W1520449809","https://openalex.org/W1522301498","https://openalex.org/W1647671624","https://openalex.org/W1665214252","https://openalex.org/W1721115786","https://openalex.org/W2033922434","https://openalex.org/W2100495367","https://openalex.org/W2117278770","https://openalex.org/W2124725212","https://openalex.org/W2125257468","https://openalex.org/W2132782512","https://openalex.org/W2134800885","https://openalex.org/W2140372282","https://openalex.org/W2144555877","https://openalex.org/W2146574666","https://openalex.org/W2153013403","https://openalex.org/W2153579005","https://openalex.org/W2170527467","https://openalex.org/W2212703438","https://openalex.org/W2252000648","https://openalex.org/W2315316408","https://openalex.org/W2538523173","https://openalex.org/W2555428947","https://openalex.org/W2589277916","https://openalex.org/W2595715041","https://openalex.org/W2740433069","https://openalex.org/W2741494657","https://openalex.org/W2759575900","https://openalex.org/W2785047343","https://openalex.org/W2798416860","https://openalex.org/W2803237843","https://openalex.org/W2805583812","https://openalex.org/W2810035278","https://openalex.org/W2888555799","https://openalex.org/W2899310090","https://openalex.org/W2903193068","https://openalex.org/W2925188774","https://openalex.org/W2936597270","https://openalex.org/W2962801832","https://openalex.org/W2962863357","https://openalex.org/W2963109131","https://openalex.org/W2963250244","https://openalex.org/W2963266340","https://openalex.org/W2963267786","https://openalex.org/W2963347649","https://openalex.org/W2963403868","https://openalex.org/W2963881719","https://openalex.org/W2963975242","https://openalex.org/W2963979492","https://openalex.org/W2964082031","https://openalex.org/W2964099746","https://openalex.org/W2964121744","https://openalex.org/W2964187553","https://openalex.org/W2964258094","https://openalex.org/W2964343359","https://openalex.org/W2970868759","https://openalex.org/W2999282340","https://openalex.org/W4294170691","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3201070945","https://openalex.org/W3149659246","https://openalex.org/W3150234497","https://openalex.org/W2792951589","https://openalex.org/W3165388794","https://openalex.org/W3084906606","https://openalex.org/W2150750161","https://openalex.org/W4200158898","https://openalex.org/W4322012790","https://openalex.org/W2971487811"],"abstract_inverted_index":{"Considerable":[0],"effort":[1],"has":[2],"been":[3],"made":[4],"to":[5,39,50],"address":[6],"the":[7,41,72,95,106,114,119,134,142,147],"data":[8,47,86],"sparsity":[9],"problem":[10],"in":[11,79,94,105],"neural":[12],"grammatical":[13],"error":[14,28],"correction.":[15],"In":[16],"this":[17],"work,":[18],"we":[19,125],"propose":[20],"a":[21,37,52,61,75,80],"simple":[22],"and":[23,101,108,137,149],"surprisingly":[24],"effective":[25],"unsupervised":[26],"synthetic":[27],"generation":[29],"method":[30],"based":[31],"on":[32,65,113,146],"confusion":[33],"sets":[34],"extracted":[35],"from":[36],"spellchecker":[38],"increase":[40],"amount":[42],"of":[43,74,129],"training":[44],"data.":[45,151],"Synthetic":[46],"is":[48,87],"used":[49],"pre-train":[51],"Transformer":[53],"sequence-to-sequence":[54],"model,":[55],"which":[56],"not":[57],"only":[58],"improves":[59],"over":[60],"strong":[62],"baseline":[63],"trained":[64,145],"authentic":[66],"error-annotated":[67,85],"data,":[68],"but":[69],"also":[70],"enables":[71],"development":[73],"practical":[76],"GEC":[77],"system":[78,144],"scenario":[81],"where":[82],"little":[83],"genuine":[84],"available.":[88],"The":[89],"developed":[90],"systems":[91],"placed":[92],"first":[93],"BEA19":[96],"shared":[97],"task,":[98],"achieving":[99],"69.47":[100],"64.24":[102],"F":[103],"0.5":[104],"restricted":[107],"low-resource":[109],"tracks":[110],"respectively,":[111],"both":[112],"W&I+LOCNESS":[115],"test":[116,123],"set.":[117],"On":[118],"popular":[120],"CoNLL":[121],"2014":[122],"set,":[124],"report":[126],"state-of-theart":[127],"results":[128],"64.16":[130],"M":[131,139],"2":[132,140],"for":[133,141],"submitted":[135],"system,":[136],"61.30":[138],"constrained":[143],"NUCLE":[148],"Lang-8":[150]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":36},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":48},{"year":2020,"cited_by_count":44},{"year":2019,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}