{"id":"https://openalex.org/W2888824653","doi":"https://doi.org/10.18653/v1/d18-1028","title":"WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse","display_name":"WikiAtomicEdits: A Multilingual Corpus of Wikipedia Edits for Modeling Language and Discourse","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2888824653","doi":"https://doi.org/10.18653/v1/d18-1028","mag":"2888824653"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1028","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1028","pdf_url":"https://www.aclweb.org/anthology/D18-1028.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1028.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014855689","display_name":"Manaal Faruqui","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Manaal Faruqui","raw_affiliation_strings":["Google AI"],"affiliations":[{"raw_affiliation_string":"Google AI","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053850863","display_name":"Ellie Pavlick","orcid":"https://orcid.org/0000-0002-7155-5420"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ellie Pavlick","raw_affiliation_strings":["Google AI"],"affiliations":[{"raw_affiliation_string":"Google AI","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082431329","display_name":"Ian Tenney","orcid":"https://orcid.org/0000-0002-6225-9283"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Tenney","raw_affiliation_strings":["Google AI"],"affiliations":[{"raw_affiliation_string":"Google AI","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021055773","display_name":"Dipanjan Das","orcid":"https://orcid.org/0000-0003-2325-0646"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dipanjan Das","raw_affiliation_strings":["Google AI"],"affiliations":[{"raw_affiliation_string":"Google AI","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014855689"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":3.2152,"has_fulltext":true,"cited_by_count":40,"citation_normalized_percentile":{"value":0.93574432,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8228986263275146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7330552339553833},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6481875777244568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.598310112953186},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.573712944984436},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5645683407783508},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4853047728538513},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4769119918346405},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.40350809693336487},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08000868558883667},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.07449528574943542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8228986263275146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7330552339553833},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6481875777244568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.598310112953186},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.573712944984436},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5645683407783508},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4853047728538513},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4769119918346405},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.40350809693336487},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08000868558883667},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.07449528574943542},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1028","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1028","pdf_url":"https://www.aclweb.org/anthology/D18-1028.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1028","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1028","pdf_url":"https://www.aclweb.org/anthology/D18-1028.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2888824653.pdf","grobid_xml":"https://content.openalex.org/works/W2888824653.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W43022990","https://openalex.org/W48507986","https://openalex.org/W78382366","https://openalex.org/W190467925","https://openalex.org/W1486649854","https://openalex.org/W1638924786","https://openalex.org/W2081809321","https://openalex.org/W2101105183","https://openalex.org/W2117134415","https://openalex.org/W2121879602","https://openalex.org/W2125527113","https://openalex.org/W2130200371","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2143230354","https://openalex.org/W2145079630","https://openalex.org/W2148517649","https://openalex.org/W2152667709","https://openalex.org/W2228826686","https://openalex.org/W2250539671","https://openalex.org/W2251347963","https://openalex.org/W2252011030","https://openalex.org/W2252123752","https://openalex.org/W2259472270","https://openalex.org/W2610858497","https://openalex.org/W2611669587","https://openalex.org/W2758097047","https://openalex.org/W2761988601","https://openalex.org/W2951714314","https://openalex.org/W2962739339","https://openalex.org/W2962772361","https://openalex.org/W2963018920","https://openalex.org/W2963572611","https://openalex.org/W2963667932","https://openalex.org/W2963732644","https://openalex.org/W2963756346","https://openalex.org/W2963768438","https://openalex.org/W2963918774","https://openalex.org/W2964308564","https://openalex.org/W4213110684","https://openalex.org/W4294367149","https://openalex.org/W4297801177","https://openalex.org/W4302343710"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W2039546652","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196"],"abstract_inverted_index":{"We":[0,46,89],"release":[1,90],"a":[2,26,31,38,95],"corpus":[3,93],"of":[4,22,78],"43":[5],"million":[6],"atomic":[7],"edits":[8,13,74],"across":[9],"8":[10],"languages.":[11],"These":[12],"are":[14],"mined":[15],"from":[16,60],"Wikipedia":[17],"edit":[18],"history":[19],"and":[20,69,80,104],"consist":[21],"instances":[23],"in":[24,66,101],"which":[25],"human":[27],"editor":[28],"has":[29],"inserted":[30],"single":[32,39],"contiguous":[33,40],"phrase":[34,41],"into,":[35],"or":[36],"deleted":[37],"from,":[42],"an":[43],"existing":[44],"sentence.":[45],"use":[47],"the":[48,54,61,91],"collected":[49],"data":[50],"to":[51,97],"show":[52],"that":[53,63,70],"language":[55,62],"generated":[56],"during":[57],"editing":[58],"differs":[59],"we":[64],"observe":[65],"standard":[67],"corpora,":[68],"models":[71,83],"trained":[72,84],"on":[73,85],"encode":[75],"different":[76],"aspects":[77],"semantics":[79],"discourse":[81],"than":[82],"raw,":[86],"unstructured":[87],"text.":[88],"full":[92],"as":[94],"resource":[96],"aid":[98],"ongoing":[99],"research":[100],"semantics,":[102],"discourse,":[103],"representation":[105],"learning.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}
