{"id":"https://openalex.org/W3207900243","doi":"https://doi.org/10.20944/preprints202110.0199.v1","title":"The Suboptimal WMT Test Sets and Its Impact on Human Parity","display_name":"The Suboptimal WMT Test Sets and Its Impact on Human Parity","publication_year":2021,"publication_date":"2021-10-13","ids":{"openalex":"https://openalex.org/W3207900243","doi":"https://doi.org/10.20944/preprints202110.0199.v1","mag":"3207900243"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202110.0199.v1","doi":"https://doi.org/10.20944/preprints202110.0199.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202110.0199.v1","pdf_url":"https://www.preprints.org/manuscript/202110.0199/v1/download","source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.preprints.org/manuscript/202110.0199/v1/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025476926","display_name":"Ahrii Kim","orcid":"https://orcid.org/0000-0003-2989-3220","observed_orcids":["https://orcid.org/0000-0003-2989-3220"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ahrii Kim","raw_affiliation_strings":["Carnegie Mellon University","Kakao Enterprise \u00a7 Carnegie Mellon University"],"raw_orcid":"https://orcid.org/0000-0003-2989-3220","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Kakao Enterprise \u00a7 Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049751816","display_name":"Yunju Bak","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunju Bak","raw_affiliation_strings":["Carnegie Mellon University","Kakao Enterprise \u00a7 Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Kakao Enterprise \u00a7 Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072023102","display_name":"Jimin Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405260795","display_name":"Kakao Enterprise (South Korea)","ror":"https://ror.org/049enk825","country_code":"KR","type":"company","lineage":["https://openalex.org/I4405259708","https://openalex.org/I4405260795"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["KR","US"],"is_corresponding":true,"raw_author_name":"Jimin Sun","raw_affiliation_strings":["Kakao Enterprise","Kakao Enterprise \u00a7 Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kakao Enterprise","institution_ids":["https://openalex.org/I4405260795"]},{"raw_affiliation_string":"Kakao Enterprise \u00a7 Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050189497","display_name":"Sungwon Lyu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sungwon Lyu","raw_affiliation_strings":["Carnegie Mellon University","Kakao Enterprise \u00a7 Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Kakao Enterprise \u00a7 Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":null,"display_name":"Changmin Lee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Changmin Lee","raw_affiliation_strings":["Carnegie Mellon University","Kakao Enterprise \u00a7 Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Kakao Enterprise \u00a7 Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025476926","https://openalex.org/A5049751816","https://openalex.org/A5050189497","https://openalex.org/A5072023102"],"corresponding_institution_ids":["https://openalex.org/I4405260795","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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":0.9961000084877014,"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":0.0017000000225380063,"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/T10759","display_name":"Translation Studies and Practices","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.6218737363815308},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5995199084281921},{"id":"https://openalex.org/C2777151079","wikidata":"https://www.wikidata.org/wiki/Q141160","display_name":"Parity (physics)","level":2,"score":0.5993793606758118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5473289489746094},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5091039538383484},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46254298090934753},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4348735213279724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3566311001777649},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.08644154667854309},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C109214941","wikidata":"https://www.wikidata.org/wiki/Q18334","display_name":"Particle physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.20944/preprints202110.0199.v1","doi":"https://doi.org/10.20944/preprints202110.0199.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202110.0199.v1","pdf_url":"https://www.preprints.org/manuscript/202110.0199/v1/download","source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.20944/preprints202110.0199.v1","doi":"https://doi.org/10.20944/preprints202110.0199.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202110.0199.v1","pdf_url":"https://www.preprints.org/manuscript/202110.0199/v1/download","source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3207900243.pdf","grobid_xml":"https://content.openalex.org/works/W3207900243.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2053154970","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2250342921","https://openalex.org/W2512924740","https://openalex.org/W2513073850","https://openalex.org/W2595715041","https://openalex.org/W2626778328","https://openalex.org/W2794365787","https://openalex.org/W2798362442","https://openalex.org/W2888159079","https://openalex.org/W2896457183","https://openalex.org/W2903193068","https://openalex.org/W2922158773","https://openalex.org/W2952103439","https://openalex.org/W2967600676","https://openalex.org/W3013197936","https://openalex.org/W3025111163","https://openalex.org/W3104976898","https://openalex.org/W3106146701","https://openalex.org/W6725857009","https://openalex.org/W6767250937","https://openalex.org/W6898505805","https://openalex.org/W7075682760"],"related_works":["https://openalex.org/W2889482553","https://openalex.org/W3025111163","https://openalex.org/W2888159079","https://openalex.org/W4385305818","https://openalex.org/W3103979400","https://openalex.org/W3106146701","https://openalex.org/W2964747975","https://openalex.org/W4289398562","https://openalex.org/W2794365787","https://openalex.org/W2971043182"],"abstract_inverted_index":{"With":[0],"the":[1,7,9,18,38,42,47,72,96,118,125,132,137,141,149],"advent":[2],"of":[3,11,41,46,61,67,79,95,127,140,148,151,173],"Neural":[4],"Machine":[5],"Translation,":[6],"more":[8,19],"achievement":[10],"human-machine":[12],"parity":[13,58,104],"is":[14,131],"claimed":[15],"at":[16,50],"WMT,":[17],"we":[20,35,63],"come":[21],"to":[22,54,108,135,162,179,190],"ask":[23],"ourselves":[24],"if":[25],"their":[26],"evaluation":[27],"environment":[28],"can":[29],"be":[30,109,183],"trusted.":[31],"In":[32],"this":[33],"paper,":[34],"argue":[36],"that":[37,88,98,160,178],"low":[39],"quality":[40],"source":[43],"test":[44,142],"set":[45,143],"news":[48],"track":[49],"WMT":[51],"may":[52],"lead":[53],"an":[55,77,191],"overrated":[56],"human":[57,103,152],"claim.":[59],"First":[60],"all,":[62],"report":[64],"nine":[65],"types":[66],"so-called":[68],"technical":[69],"contaminants":[70],"in":[71],"data":[73],"set,":[74],"originated":[75],"from":[76],"absence":[78],"meticulous":[80],"inspection":[81],"after":[82],"web-crawling.":[83],"Our":[84],"empirical":[85],"findings":[86],"show":[87],"when":[89,117,187],"they":[90],"are":[91,121],"corrected,":[92],"about":[93],"5%":[94],"segments":[97],"have":[99],"previously":[100],"achieved":[101],"a":[102,113,145,170,184],"claim":[105],"turn":[106],"out":[107],"statistically":[110],"invalid.":[111],"Such":[112],"tendency":[114],"gets":[115],"evident":[116],"contaminated":[119],"sentences":[120],"solely":[122],"concerned.":[123],"To":[124],"best":[126],"our":[128],"knowledge,":[129],"it":[130,181,188],"first":[133],"attempt":[134],"question":[136],"\u201csource\u201d":[138],"side":[139],"as":[144],"potential":[146],"cause":[147],"overclaim":[150],"parity.":[153],"We":[154,176],"cast":[155],"evidence":[156],"for":[157],"such":[158],"phenomenon":[159],"according":[161],"sentence-level":[163],"TER":[164],"scores,":[165],"those":[166],"trivial":[167],"errors":[168],"change":[169],"good":[171],"part":[172],"system":[174],"translations.":[175],"conclude":[177],"overlook":[180],"would":[182],"mistake,":[185],"especially":[186],"comes":[189],"NMT":[192],"evaluation.":[193]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2021-10-25T00:00:00"}