{"id":"https://openalex.org/W3007253491","doi":"https://doi.org/10.1109/bigdata47090.2019.9005618","title":"Extracting Grammatical Error Corrections from Wikipedia Revision History","display_name":"Extracting Grammatical Error Corrections from Wikipedia Revision History","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007253491","doi":"https://doi.org/10.1109/bigdata47090.2019.9005618","mag":"3007253491"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9005618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9005618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027106484","display_name":"Jhih-Jie Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jhih-Jie Chen","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108271875","display_name":"Yi-Dong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Dong Wu","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103917463","display_name":"Yu-Chuan Tai","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Chuan Tai","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008545952","display_name":"Ching\u2010Yu Yang","orcid":"https://orcid.org/0000-0001-8986-0119"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ching-Yu Yang","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110668312","display_name":"Hai-Lun Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hai-Lun Tu","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016135743","display_name":"Jason S. Chang","orcid":"https://orcid.org/0000-0002-8227-7382"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jason S. Chang","raw_affiliation_strings":["Department of Computer Science, National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20024198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2019","issue":null,"first_page":"6016","last_page":"6018"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.927299976348877,"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":0.7766919136047363},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7361096739768982},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6508998870849609},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5770596861839294},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5522732734680176},{"id":"https://openalex.org/keywords/error-analysis","display_name":"Error analysis","score":0.5158995389938354},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5135312676429749},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.49790287017822266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49182820320129395},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15969443321228027},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1346137523651123},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07349243760108948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766919136047363},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7361096739768982},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6508998870849609},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5770596861839294},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5522732734680176},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.5158995389938354},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5135312676429749},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.49790287017822266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49182820320129395},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15969443321228027},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1346137523651123},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07349243760108948},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9005618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9005618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"mag:3044090036","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002269259982916","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6800000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W43022990","https://openalex.org/W48507986","https://openalex.org/W2123388068","https://openalex.org/W2145079630","https://openalex.org/W2554764206","https://openalex.org/W2741494657","https://openalex.org/W2760051178","https://openalex.org/W6601815518","https://openalex.org/W6601969435","https://openalex.org/W6678528935","https://openalex.org/W6681773965","https://openalex.org/W6729818218"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2380243770","https://openalex.org/W2377495875","https://openalex.org/W2390973415","https://openalex.org/W2074837817"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,77,91],"process":[4,55],"of":[5,96],"extracting":[6],"and":[7,35,51,70,100],"filtering":[8],"Wikipedia":[9,22],"revision":[10,23],"history":[11,24],"as":[12],"a":[13],"resource":[14],"for":[15],"grammatical":[16,28],"error":[17,29,47,104],"correction":[18,78],"(GEC).":[19],"Edits":[20],"in":[21,58],"vary":[25],"widely,":[26],"including":[27],"corrections,":[30],"information":[31],"supplements,":[32],"format":[33],"amendments,":[34],"even":[36],"vandalism.":[37],"To":[38],"extract":[39],"only":[40,76],"GEC-related":[41,68],"revisions,":[42],"we":[43,64],"use":[44],"an":[45],"automated":[46],"annotation":[48],"toolkit,":[49],"ERRANT1,":[50],"extend":[52],"it":[53],"to":[54,87],"large":[56],"data":[57],"parallel":[59,97],"efficiently.":[60],"With":[61],"error-type":[62],"analysis,":[63],"can":[65],"then":[66],"identify":[67],"edits":[69,74],"omit":[71],"other":[72],"unrelated":[73],"(i.e.,":[75],"parts":[79],"are":[80],"reserved).":[81],"The":[82],"resulting":[83],"corpus":[84,95],"is":[85],"-":[86,90],"our":[88],"knowledge":[89],"largest":[92],"publicly":[93],"available":[94],"possibly":[98],"erroneous":[99],"correct":[101],"sentences":[102],"with":[103],"type":[105],"labels.":[106]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
