{"id":"https://openalex.org/W2911227954","doi":"https://doi.org/10.1162/tacl_a_00041","title":"Data Statements for Natural Language Processing: Toward Mitigating System Bias and Enabling Better Science","display_name":"Data Statements for Natural Language Processing: Toward Mitigating System Bias and Enabling Better Science","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2911227954","doi":"https://doi.org/10.1162/tacl_a_00041","mag":"2911227954"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00041","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00041","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00041/1567666/tacl_a_00041.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00041/1567666/tacl_a_00041.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023750515","display_name":"Emily M. Bender","orcid":"https://orcid.org/0000-0001-5384-6227"},"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":"Emily M. Bender","raw_affiliation_strings":["Department of Linguistics, University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics, University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002491750","display_name":"Batya Friedman","orcid":null},"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":"Batya Friedman","raw_affiliation_strings":["The Information School, University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Information School, University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002491750","https://openalex.org/A5023750515"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":52.433,"has_fulltext":true,"cited_by_count":823,"citation_normalized_percentile":{"value":0.99878251,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"6","issue":null,"first_page":"587","last_page":"604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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":0.9979000091552734,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/embarrassment","display_name":"Embarrassment","score":0.7871450185775757},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7177626490592957},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5557337999343872},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5493245124816895},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5442474484443665},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4724947512149811},{"id":"https://openalex.org/keywords/lead","display_name":"Lead (geology)","score":0.44757112860679626},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4211839735507965},{"id":"https://openalex.org/keywords/engineering-ethics","display_name":"Engineering ethics","score":0.35357666015625},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.25016623735427856},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12863025069236755},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09418195486068726}],"concepts":[{"id":"https://openalex.org/C2776716606","wikidata":"https://www.wikidata.org/wiki/Q1761451","display_name":"Embarrassment","level":2,"score":0.7871450185775757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7177626490592957},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5557337999343872},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5493245124816895},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5442474484443665},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4724947512149811},{"id":"https://openalex.org/C2777093003","wikidata":"https://www.wikidata.org/wiki/Q6508345","display_name":"Lead (geology)","level":2,"score":0.44757112860679626},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4211839735507965},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.35357666015625},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25016623735427856},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12863025069236755},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09418195486068726},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00041","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00041","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00041/1567666/tacl_a_00041.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:428b6ffd19f449f294f12c42fdb96aad","is_oa":false,"landing_page_url":"https://doaj.org/article/428b6ffd19f449f294f12c42fdb96aad","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 6 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00041","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00041","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00041/1567666/tacl_a_00041.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G2712191288","display_name":"HCC: Medium: Multi-lifespan Information System Research and Design","funder_award_id":"1302709","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6757341107","display_name":null,"funder_award_id":"IIS-1302709","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"},{"id":"https://openalex.org/F4320319918","display_name":"York University","ror":"https://ror.org/05fq50484"},{"id":"https://openalex.org/F4320320591","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89"},{"id":"https://openalex.org/F4320332603","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2911227954.pdf","grobid_xml":"https://content.openalex.org/works/W2911227954.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W128245317","https://openalex.org/W147871884","https://openalex.org/W1485490758","https://openalex.org/W1535357018","https://openalex.org/W1632114991","https://openalex.org/W1636536540","https://openalex.org/W1870418615","https://openalex.org/W1982697162","https://openalex.org/W2006447892","https://openalex.org/W2017538178","https://openalex.org/W2032541700","https://openalex.org/W2038997150","https://openalex.org/W2062783322","https://openalex.org/W2077601832","https://openalex.org/W2089064175","https://openalex.org/W2089179911","https://openalex.org/W2097606805","https://openalex.org/W2123276999","https://openalex.org/W2132301897","https://openalex.org/W2142650094","https://openalex.org/W2155765950","https://openalex.org/W2166706824","https://openalex.org/W2250559305","https://openalex.org/W2250710744","https://openalex.org/W2251210340","https://openalex.org/W2252027930","https://openalex.org/W2263936035","https://openalex.org/W2279316390","https://openalex.org/W2293387883","https://openalex.org/W2473555522","https://openalex.org/W2483215953","https://openalex.org/W2511234952","https://openalex.org/W2554719826","https://openalex.org/W2563826943","https://openalex.org/W2579198251","https://openalex.org/W2607719644","https://openalex.org/W2623515145","https://openalex.org/W2741636242","https://openalex.org/W2769882943","https://openalex.org/W2795038878","https://openalex.org/W2798497570","https://openalex.org/W2802105481","https://openalex.org/W2962787423","https://openalex.org/W3040519024","https://openalex.org/W3123388499","https://openalex.org/W4213158633"],"related_works":["https://openalex.org/W1909482326","https://openalex.org/W2315799286","https://openalex.org/W1746611774","https://openalex.org/W2380005826","https://openalex.org/W2001398865","https://openalex.org/W1807980626","https://openalex.org/W3136826123","https://openalex.org/W2792677744","https://openalex.org/W4247610522","https://openalex.org/W81782365"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"data":[5,31,50,67,86],"statements":[6,68,87],"as":[7,78],"a":[8,64],"design":[9],"solution":[10],"and":[11,22,27,41,71,95,114,124,140],"professional":[12],"practice":[13],"for":[14,59],"natural":[15,108],"language":[16,98,109,128],"processing":[17,110],"technologists,":[18],"in":[19,54,97,104,134],"both":[20],"research":[21,111],"development.":[23],"Through":[24],"the":[25,33,47,55,73],"adoption":[26],"widespread":[28],"use":[29,48],"of":[30,49,57,75,80],"statements,":[32],"field":[34],"can":[35,69,112],"begin":[36],"to":[37,93,101,127,146],"address":[38],"critical":[39],"scientific":[40],"ethical":[42],"issues":[43,91],"that":[44,66,85,130],"result":[45],"from":[46,51,121],"certain":[52],"populations":[53],"development":[56],"technology":[58,129],"other":[60],"populations.":[61],"We":[62,83],"present":[63],"form":[65],"take":[70],"explore":[72],"implications":[74],"adopting":[76],"them":[77,145],"part":[79],"regular":[81],"practice.":[82],"argue":[84],"will":[88],"help":[89],"alleviate":[90],"related":[92],"exclusion":[94],"bias":[96],"technology,":[99],"lead":[100,126],"better":[102,116],"precision":[103],"claims":[105],"about":[106],"how":[107],"generalize":[113],"thus":[115],"engineering":[117],"results,":[118],"protect":[119],"companies":[120],"public":[122],"embarrassment,":[123],"ultimately":[125],"meets":[131],"its":[132],"users":[133],"their":[135],"own":[136],"preferred":[137],"linguistic":[138],"style":[139],"furthermore":[141],"does":[142],"not":[143],"misrepresent":[144],"others.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":61},{"year":2025,"cited_by_count":94},{"year":2024,"cited_by_count":107},{"year":2023,"cited_by_count":155},{"year":2022,"cited_by_count":126},{"year":2021,"cited_by_count":178},{"year":2020,"cited_by_count":80},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}
