{"id":"https://openalex.org/W2470681840","doi":"https://doi.org/10.18653/v1/n16-1001","title":"Achieving Accurate Conclusions in Evaluation of Automatic Machine Translation Metrics","display_name":"Achieving Accurate Conclusions in Evaluation of Automatic Machine Translation Metrics","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2470681840","doi":"https://doi.org/10.18653/v1/n16-1001","mag":"2470681840"},"language":"en","primary_location":{"id":"doi:10.18653/v1/n16-1001","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-1001","pdf_url":"https://www.aclweb.org/anthology/N16-1001.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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/N16-1001.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020500064","display_name":"Yvette Graham","orcid":"https://orcid.org/0000-0001-6741-4855"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yvette Graham","raw_affiliation_strings":["School of Computing Dublin City University"],"affiliations":[{"raw_affiliation_string":"School of Computing Dublin City University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100426170","display_name":"Qun Liu","orcid":"https://orcid.org/0000-0002-7000-1792"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Qun Liu","raw_affiliation_strings":["ADAPT Research Centre Dublin City University"],"affiliations":[{"raw_affiliation_string":"ADAPT Research Centre Dublin City University","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020500064"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3007,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.95847984,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"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/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9965999722480774,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9965000152587891,"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/metric","display_name":"Metric (unit)","score":0.8732364177703857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483835220336914},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.6882431507110596},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6474136114120483},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5731546878814697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5483754277229309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.530741274356842},{"id":"https://openalex.org/keywords/bleu","display_name":"BLEU","score":0.5295774936676025},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5269537568092346},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4602663815021515},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.45559266209602356},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4282541871070862},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39143434166908264},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16047650575637817},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07420802116394043},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06298357248306274}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.8732364177703857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483835220336914},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.6882431507110596},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6474136114120483},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5731546878814697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5483754277229309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.530741274356842},{"id":"https://openalex.org/C622187","wikidata":"https://www.wikidata.org/wiki/Q3500773","display_name":"BLEU","level":3,"score":0.5295774936676025},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5269537568092346},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4602663815021515},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.45559266209602356},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4282541871070862},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39143434166908264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16047650575637817},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07420802116394043},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06298357248306274},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/n16-1001","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-1001","pdf_url":"https://www.aclweb.org/anthology/N16-1001.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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},{"id":"pmh:http://www.rian.ie/164436/","is_oa":false,"landing_page_url":"http://doras.dcu.ie/23194/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Graham, Yvette and Liu, Qun ORCID: 0000-0002-7000-1792 <https://orcid.org/0000-0002-7000-1792>  (2016) Achieving accurate conclusions in evaluation of automatic machine translation metrics.  In: 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), 12-17 June 2016, San Diego, CA. USA.  ISBN 978-1-941643-91-4","raw_type":"Other"},{"id":"pmh:http://www.rian.ie/164496/","is_oa":false,"landing_page_url":"http://doras.dcu.ie/23208/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I115570527","host_organization_name":"Dublin Institute of Technology","host_organization_lineage":["https://openalex.org/I115570527"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Graham, Yvette and Liu, Qun ORCID: 0000-0002-7000-1792 <https://orcid.org/0000-0002-7000-1792>  (2016) Achieving accurate conclusions in evaluation of automatic machine translation metrics.  In: 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 12-15 June 2016, San Diego, Ca. USA.","raw_type":"Other"}],"best_oa_location":{"id":"doi:10.18653/v1/n16-1001","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-1001","pdf_url":"https://www.aclweb.org/anthology/N16-1001.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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1076797115","display_name":null,"funder_award_id":"co-funded","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G228147372","display_name":null,"funder_award_id":"Grant 13/RC/2106","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G2563910032","display_name":null,"funder_award_id":"13/RC/2106","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G3514550006","display_name":null,"funder_award_id":"Centre","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3875748329","display_name":null,"funder_award_id":"European Regional Development Fund","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3993907298","display_name":null,"funder_award_id":"13/RC/2106","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5399556803","display_name":null,"funder_award_id":"This project has received funding from the Europea","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7300706396","display_name":null,"funder_award_id":"European Union Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8538941428","display_name":null,"funder_award_id":"Regional Development Fund","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8884546066","display_name":"QT21: Quality Translation 21","funder_award_id":"645452","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320320865","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2470681840.pdf","grobid_xml":"https://content.openalex.org/works/W2470681840.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1966359789","https://openalex.org/W2101105183","https://openalex.org/W2250234233","https://openalex.org/W2251482987","https://openalex.org/W2251610689","https://openalex.org/W2251994258","https://openalex.org/W2252166243","https://openalex.org/W2915756181","https://openalex.org/W2916548775","https://openalex.org/W2917452219"],"related_works":["https://openalex.org/W2099607809","https://openalex.org/W2395641992","https://openalex.org/W3021126373","https://openalex.org/W2807475932","https://openalex.org/W4280571180","https://openalex.org/W2341457423","https://openalex.org/W2903057408","https://openalex.org/W92588874","https://openalex.org/W2426188458","https://openalex.org/W2121771196"],"abstract_inverted_index":{"Automatic":[0],"Machine":[1],"Translation":[2],"metrics,":[3],"such":[4],"as":[5,13],"BLEU,":[6],"are":[7,78],"widely":[8],"used":[9],"in":[10,60,68,81,109,117,156,162],"empirical":[11],"evaluation":[12,163],"a":[14,23,37,42,48,140,149],"substitute":[15],"for":[16,73],"human":[17,34,76],"assessment.":[18],"Subsequently,":[19],"the":[20,57,91,129,165],"performance":[21,167],"of":[22,31,47,114,126,128,139,152,164,168],"given":[24],"metric":[25,40,69,82,118],"is":[26,51],"measured":[27],"by":[28],"its":[29],"strength":[30],"correlation":[32,44,61,105],"with":[33,75],"judgment.":[35],"When":[36],"newly":[38],"proposed":[39],"achieves":[41,158],"stronger":[43],"over":[45],"that":[46,131,142,155],"baseline,":[49],"it":[50],"important":[52],"to":[53,65,134],"take":[54],"into":[55],"account":[56],"uncertainty":[58],"inherent":[59],"point":[62],"estimates":[63],"prior":[64],"concluding":[66],"improvements":[67],"performance.":[70,119],"Confidence":[71],"intervals":[72],"correlations":[74],"judgment":[77],"rarely":[79],"reported":[80],"evaluations,":[83],"however,":[84],"and":[85],"when":[86],"they":[87],"have":[88,95],"been":[89,98],"reported,":[90],"most":[92],"suitable":[93],"methods":[94],"unfortunately":[96],"not":[97],"applied.":[99],"For":[100],"example,":[101],"incorrect":[102],"assumptions":[103],"about":[104],"sampling":[106,154],"distributions":[107],"made":[108],"past":[110],"evaluations":[111],"risk":[112],"over-estimation":[113],"significant":[115],"differences":[116],"In":[120],"this":[121],"paper,":[122],"we":[123,147],"provide":[124],"analysis":[125],"each":[127],"issues":[130],"may":[132],"lead":[133],"inaccuracies":[135],"before":[136],"providing":[137],"detail":[138],"method":[141,151],"overcomes":[143],"previous":[144],"challenges.":[145],"Additionally,":[146],"propose":[148],"new":[150],"translation":[153],"contrast":[157],"genuine":[159],"high":[160],"conclusivity":[161],"relative":[166],"metrics.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}