{"id":"https://openalex.org/W4300860593","doi":"https://doi.org/10.48550/arxiv.2203.15858","title":"Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics","display_name":"Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics","publication_year":2022,"publication_date":"2022-03-29","ids":{"openalex":"https://openalex.org/W4300860593","doi":"https://doi.org/10.48550/arxiv.2203.15858"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2203.15858","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15858","pdf_url":"https://arxiv.org/pdf/2203.15858","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.15858","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100562747","display_name":"Jiannan Xiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang, Jiannan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101425369","display_name":"Huayang Li","orcid":"https://orcid.org/0000-0003-3539-8648"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Huayang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375505","display_name":"Yahui Liu","orcid":"https://orcid.org/0000-0002-6889-4763"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yahui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005411806","display_name":"Lemao Liu","orcid":"https://orcid.org/0000-0003-3804-5768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Lemao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070016752","display_name":"Guoping Huang","orcid":"https://orcid.org/0000-0002-6795-9596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Guoping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085254654","display_name":"Defu Lian","orcid":"https://orcid.org/0000-0002-3507-9607"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lian, Defu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087920747","display_name":"Shuming Shi","orcid":"https://orcid.org/0000-0001-7018-0682"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Shuming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.9962000250816345,"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":0.9962000250816345,"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":0.9937999844551086,"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":0.9800999760627747,"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/variance","display_name":"Variance (accounting)","score":0.7870296239852905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7309085726737976},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.721267819404602},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7166361212730408},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5368841886520386},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5271834135055542},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49974989891052246},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.45988333225250244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4339357912540436},{"id":"https://openalex.org/keywords/independent-and-identically-distributed-random-variables","display_name":"Independent and identically distributed random variables","score":0.4288768172264099},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40949660539627075},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.27973049879074097},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15530556440353394},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.05536496639251709}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.7870296239852905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7309085726737976},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.721267819404602},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7166361212730408},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5368841886520386},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5271834135055542},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49974989891052246},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.45988333225250244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4339357912540436},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.4288768172264099},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40949660539627075},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27973049879074097},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15530556440353394},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.05536496639251709},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2203.15858","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15858","pdf_url":"https://arxiv.org/pdf/2203.15858","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2203.15858","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.15858","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.15858","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.15858","pdf_url":"https://arxiv.org/pdf/2203.15858","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3004218185","https://openalex.org/W4390241083","https://openalex.org/W4245457074","https://openalex.org/W2323735050","https://openalex.org/W2347733609","https://openalex.org/W2912990606","https://openalex.org/W1717256175","https://openalex.org/W51364034","https://openalex.org/W2898073868","https://openalex.org/W4284663758"],"abstract_inverted_index":{"Current":[0],"practices":[1],"in":[2,13,21],"metric":[3],"evaluation":[4,45],"focus":[5],"on":[6,48,108],"one":[7],"single":[8,110],"dataset,":[9,111],"e.g.,":[10],"Newstest":[11],"dataset":[12],"each":[14],"year's":[15],"WMT":[16],"Metrics":[17],"Shared":[18],"Task.":[19],"However,":[20],"this":[22,52],"paper,":[23],"we":[24],"qualitatively":[25],"and":[26,63,68,101],"quantitatively":[27],"show":[28],"that":[29,88],"the":[30,44,64,78,106],"performances":[31],"of":[32,40,66,80,121],"metrics":[33,41],"are":[34],"sensitive":[35],"to":[36,104,116],"data.":[37],"The":[38],"ranking":[39],"varies":[42],"when":[43,89],"is":[46],"conducted":[47],"different":[49],"datasets.":[50,123],"Then":[51],"paper":[53],"further":[54],"investigates":[55],"two":[56],"potential":[57],"hypotheses,":[58],"i.e.,":[59],"insignificant":[60],"data":[61,81,97],"points":[62],"deviation":[65],"Independent":[67],"Identically":[69],"Distributed":[70],"(i.i.d)":[71],"assumption,":[72],"which":[73],"may":[74,114],"take":[75,96],"responsibility":[76],"for":[77],"issue":[79],"variance.":[82],"In":[83],"conclusion,":[84],"our":[85],"findings":[86],"suggest":[87],"evaluating":[90],"automatic":[91],"translation":[92],"metrics,":[93],"researchers":[94],"should":[95],"variance":[98],"into":[99],"account":[100],"be":[102],"cautious":[103],"claim":[105],"result":[107],"a":[109],"because":[112],"it":[113],"leads":[115],"inconsistent":[117],"results":[118],"with":[119],"most":[120],"other":[122]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2022-10-04T00:00:00"}