{"id":"https://openalex.org/W2951243568","doi":"https://doi.org/10.18653/v1/p19-1267","title":"We Need to Talk about Standard Splits","display_name":"We Need to Talk about Standard Splits","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2951243568","doi":"https://doi.org/10.18653/v1/p19-1267","mag":"2951243568","pmid":"https://pubmed.ncbi.nlm.nih.gov/37351085"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p19-1267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1267","pdf_url":"https://www.aclweb.org/anthology/P19-1267.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","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P19-1267.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011757745","display_name":"Kyle Gorman","orcid":"https://orcid.org/0000-0002-4233-6595"},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kyle Gorman","raw_affiliation_strings":["City University of New York"],"affiliations":[{"raw_affiliation_string":"City University of New York","institution_ids":["https://openalex.org/I174216632"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044068445","display_name":"Steven Bedrick","orcid":"https://orcid.org/0000-0002-0163-9397"},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Bedrick","raw_affiliation_strings":["Oregon Health & Science University"],"affiliations":[{"raw_affiliation_string":"Oregon Health & Science University","institution_ids":["https://openalex.org/I165690674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011757745"],"corresponding_institution_ids":["https://openalex.org/I174216632"],"apc_list":null,"apc_paid":null,"fwci":10.6952,"has_fulltext":true,"cited_by_count":95,"citation_normalized_percentile":{"value":0.98567519,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"2019","issue":null,"first_page":"2786","last_page":"2791"},"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":0.9991000294685364,"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":0.9889000058174133,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7733043432235718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.722623348236084},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.6874070763587952},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5931893587112427},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5745036602020264},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.565310001373291},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4739791750907898},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.46233484148979187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45740699768066406},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4247048497200012},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3482212424278259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3453635573387146},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2746849060058594},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12136328220367432}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7733043432235718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722623348236084},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.6874070763587952},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5931893587112427},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5745036602020264},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.565310001373291},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4739791750907898},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.46233484148979187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45740699768066406},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4247048497200012},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3482212424278259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3453635573387146},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2746849060058594},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12136328220367432},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/p19-1267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1267","pdf_url":"https://www.aclweb.org/anthology/P19-1267.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"},{"id":"pmid:37351085","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37351085","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the conference. Association for Computational Linguistics. Meeting","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10287171","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10287171","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10287171/pdf/nihms-1908534.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Conf Assoc Comput Linguist Meet","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.18653/v1/p19-1267","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p19-1267","pdf_url":"https://www.aclweb.org/anthology/P19-1267.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":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951243568.pdf","grobid_xml":"https://content.openalex.org/works/W2951243568.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1515847863","https://openalex.org/W1632114991","https://openalex.org/W1773803948","https://openalex.org/W1850558006","https://openalex.org/W1932968309","https://openalex.org/W1975004953","https://openalex.org/W2006820723","https://openalex.org/W2008652694","https://openalex.org/W2020018978","https://openalex.org/W2080637049","https://openalex.org/W2092170487","https://openalex.org/W2127635577","https://openalex.org/W2131148434","https://openalex.org/W2134899753","https://openalex.org/W2135843243","https://openalex.org/W2141766660","https://openalex.org/W2175675225","https://openalex.org/W2251964473","https://openalex.org/W2399720833","https://openalex.org/W2469900699","https://openalex.org/W2740834240","https://openalex.org/W2740840489","https://openalex.org/W2798935874","https://openalex.org/W2890774895","https://openalex.org/W2890939561","https://openalex.org/W2891288076","https://openalex.org/W2950121111","https://openalex.org/W2963583956","https://openalex.org/W2963940534","https://openalex.org/W2988304195","https://openalex.org/W4243639737","https://openalex.org/W4252578281"],"related_works":["https://openalex.org/W4205713785","https://openalex.org/W3016766501","https://openalex.org/W4398287560","https://openalex.org/W4398914716","https://openalex.org/W4398619072","https://openalex.org/W4398556994","https://openalex.org/W4398472861","https://openalex.org/W4398934068","https://openalex.org/W4398686282","https://openalex.org/W3160516639"],"abstract_inverted_index":{"It":[0],"is":[1],"standard":[2],"practice":[3],"in":[4,33,99],"speech":[5],"&":[6],"language":[7],"technology":[8],"to":[9,13,29,37,81],"rank":[10],"systems":[11],"according":[12],"performance":[14,34,73],"on":[15,74],"a":[16,75],"test":[17],"set":[18],"held":[19],"out":[20],"for":[21],"evaluation.":[22],"However,":[23],"few":[24,42],"researchers":[25],"apply":[26],"statistical":[27],"tests":[28],"determine":[30],"whether":[31],"differences":[32],"are":[35],"likely":[36],"arise":[38],"by":[39],"chance,":[40],"and":[41,56,66],"examine":[43],"the":[44],"stability":[45],"of":[46,69],"system":[47,100],"ranking":[48],"across":[49],"multiple":[50],"training-testing":[51],"splits.":[52,89],"We":[53,79,90],"conduct":[54],"replication":[55],"reproduction":[57],"experiments":[58],"with":[59],"nine":[60],"part-of-speech":[61],"taggers":[62],"published":[63],"between":[64],"2000":[65],"2018,":[67],"each":[68],"which":[70],"reports":[71],"state-of-the-art":[72],"widely-used":[76],"\"standard":[77],"split\".":[78],"fail":[80],"reliably":[82],"reproduce":[83],"some":[84],"rankings":[85],"using":[86],"<i>randomly":[87],"generated</i>":[88],"suggest":[91],"that":[92],"randomly":[93],"generated":[94],"splits":[95],"should":[96],"be":[97],"used":[98],"comparison.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":7}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}