{"id":"https://openalex.org/W2949858875","doi":"https://doi.org/10.18653/v1/p19-1073","title":"Errudite: Scalable, Reproducible, and Testable Error Analysis","display_name":"Errudite: Scalable, Reproducible, and Testable Error Analysis","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2949858875","doi":"https://doi.org/10.18653/v1/p19-1073","mag":"2949858875"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1073","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1073","pdf_url":"https://www.aclweb.org/anthology/P19-1073.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1073.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004225142","display_name":"Tongshuang Wu","orcid":"https://orcid.org/0000-0003-1630-0588"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tongshuang Wu","raw_affiliation_strings":["School of Computer Science & Engineering, University of Washington"],"affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019726734","display_name":"Marco T\u00falio Ribeiro","orcid":"https://orcid.org/0000-0002-3301-1297"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marco Tulio Ribeiro","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090570042","display_name":"Jeffrey Heer","orcid":"https://orcid.org/0000-0002-6175-1655"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Heer","raw_affiliation_strings":["School of Computer Science & Engineering, University of Washington"],"affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085011940","display_name":"Daniel S. Weld","orcid":"https://orcid.org/0000-0002-3255-0109"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Weld","raw_affiliation_strings":["School of Computer Science & Engineering, University of Washington"],"affiliations":[{"raw_affiliation_string":"School of Computer Science & Engineering, University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004225142"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":10.6939,"has_fulltext":true,"cited_by_count":131,"citation_normalized_percentile":{"value":0.98566295,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"747","last_page":"763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10260","display_name":"Software Engineering Research","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9973999857902527,"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":0.8420213460922241},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.774649977684021},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6385848522186279},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6233712434768677},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.6084286570549011},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5841220021247864},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5470224618911743},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4865962266921997},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4482175409793854},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4389817714691162},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4308466911315918},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41728633642196655},{"id":"https://openalex.org/keywords/rewriting","display_name":"Rewriting","score":0.41670626401901245},{"id":"https://openalex.org/keywords/error-analysis","display_name":"Error analysis","score":0.4140189290046692},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40829959511756897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40221303701400757},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16611039638519287},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09271523356437683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8420213460922241},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.774649977684021},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6385848522186279},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6233712434768677},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6084286570549011},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5841220021247864},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5470224618911743},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4865962266921997},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4482175409793854},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4389817714691162},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4308466911315918},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41728633642196655},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.41670626401901245},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.4140189290046692},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40829959511756897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40221303701400757},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16611039638519287},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09271523356437683},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":1,"locations":[{"id":"doi:10.18653/v1/p19-1073","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1073","pdf_url":"https://www.aclweb.org/anthology/P19-1073.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1073","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1073","pdf_url":"https://www.aclweb.org/anthology/P19-1073.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 57th Annual Meeting of the Association for Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G2637195115","display_name":null,"funder_award_id":"4-18-1-","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4238522470","display_name":null,"funder_award_id":"N00014-18-1-2193","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2949858875.pdf","grobid_xml":"https://content.openalex.org/works/W2949858875.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1560729591","https://openalex.org/W1792831685","https://openalex.org/W1933349210","https://openalex.org/W2064766209","https://openalex.org/W2070246124","https://openalex.org/W2130500927","https://openalex.org/W2131726681","https://openalex.org/W2322584079","https://openalex.org/W2342091124","https://openalex.org/W2551396370","https://openalex.org/W2587528408","https://openalex.org/W2597425697","https://openalex.org/W2607223307","https://openalex.org/W2607311634","https://openalex.org/W2608030593","https://openalex.org/W2626154462","https://openalex.org/W2740765036","https://openalex.org/W2770411433","https://openalex.org/W2785176118","https://openalex.org/W2787119853","https://openalex.org/W2793978524","https://openalex.org/W2799007037","https://openalex.org/W2886441967","https://openalex.org/W2906583754","https://openalex.org/W2906955990","https://openalex.org/W2954992865","https://openalex.org/W2962718483","https://openalex.org/W2962731754","https://openalex.org/W2962809918","https://openalex.org/W2962816513","https://openalex.org/W2962877709","https://openalex.org/W2963159735","https://openalex.org/W2963198001","https://openalex.org/W2963260436","https://openalex.org/W2963339397","https://openalex.org/W2963341493","https://openalex.org/W2963547127","https://openalex.org/W2963615251","https://openalex.org/W2963691697","https://openalex.org/W2963748441","https://openalex.org/W2963769536","https://openalex.org/W2963898730","https://openalex.org/W2963969878","https://openalex.org/W2964463555","https://openalex.org/W4239720002"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W3025615835","https://openalex.org/W4384133558","https://openalex.org/W173210993","https://openalex.org/W2390660599","https://openalex.org/W3003410553","https://openalex.org/W3113091479","https://openalex.org/W4284706735"],"abstract_inverted_index":{"Though":[0],"error":[1,40,54,137,149,156],"analysis":[2,157],"is":[3],"crucial":[4],"to":[5,71,131,162],"understanding":[6],"and":[7,27,34,42,86,135,152,164],"improving":[8],"NLP":[9],"models,":[10],"the":[11,102,155],"common":[12],"practice":[13],"of":[14,18,22,78,93,104],"manual,":[15],"subjective":[16],"categorization":[17],"a":[19,75,122],"small":[20],"sample":[21],"errors":[23,105],"can":[24],"yield":[25],"biased":[26],"incomplete":[28],"conclusions.":[29],"This":[30],"paper":[31],"codifies":[32],"model":[33],"task":[35],"agnostic":[36],"principles":[37],"for":[38,48,60],"informative":[39],"analysis,":[41],"presents":[43],"Errudite,":[44],"an":[45,66],"interactive":[46],"tool":[47],"better":[49],"supporting":[50],"this":[51,64,112],"process.":[52],"First,":[53],"groups":[55],"should":[56,80,106],"be":[57,81,107],"precisely":[58],"defined":[59],"reproducibility;":[61],"Errudite":[62,89,110,127],"supports":[63,111],"with":[65,96,121,139],"expressive":[67],"domainspecific":[68],"language.":[69],"Second,":[70],"avoid":[72],"spurious":[73],"conclusions,":[74],"large":[76],"set":[77],"instances":[79,95],"analyzed,":[82],"including":[83],"both":[84],"positive":[85],"negative":[87],"examples;":[88],"enables":[90,129],"systematic":[91],"grouping":[92],"relevant":[94],"filtering":[97],"queries.":[98],"Third,":[99],"hypotheses":[100],"about":[101],"cause":[103],"explicitly":[108],"tested;":[109],"via":[113],"automated":[114],"counterfactual":[115],"rewriting.":[116],"We":[117],"validate":[118],"our":[119],"approach":[120],"user":[123],"study,":[124],"finding":[125],"that":[126],"(1)":[128],"users":[130,161],"perform":[132],"high":[133],"quality":[134],"reproducible":[136],"analyses":[138,150],"less":[140],"effort,":[141],"(2)":[142],"reveals":[143],"substantial":[144],"ambiguities":[145],"in":[146],"prior":[147,166],"published":[148],"practices,":[151],"(3)":[153],"enhances":[154],"experience":[158],"by":[159],"allowing":[160],"test":[163],"revise":[165],"beliefs.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":37},{"year":2020,"cited_by_count":18}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}