{"id":"https://openalex.org/W2990787438","doi":"https://doi.org/10.18653/v1/w19-8642","title":"Agreement is overrated: A plea for correlation to assess human evaluation reliability","display_name":"Agreement is overrated: A plea for correlation to assess human evaluation reliability","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2990787438","doi":"https://doi.org/10.18653/v1/w19-8642","mag":"2990787438"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-8642","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8642","pdf_url":"https://www.aclweb.org/anthology/W19-8642.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 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-8642.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091520339","display_name":"Jacopo Amidei","orcid":"https://orcid.org/0000-0002-8846-252X"},"institutions":[{"id":"https://openalex.org/I204136569","display_name":"The Open University","ror":"https://ror.org/05mzfcs16","country_code":"GB","type":"education","lineage":["https://openalex.org/I204136569"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jacopo Amidei","raw_affiliation_strings":["School of Computing and Communications The Open University Milton Keynes, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Communications The Open University Milton Keynes, UK","institution_ids":["https://openalex.org/I204136569"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077974543","display_name":"Paul Piwek","orcid":"https://orcid.org/0000-0003-1621-6124"},"institutions":[{"id":"https://openalex.org/I204136569","display_name":"The Open University","ror":"https://ror.org/05mzfcs16","country_code":"GB","type":"education","lineage":["https://openalex.org/I204136569"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul Piwek","raw_affiliation_strings":["School of Computing and Communications The Open University Milton Keynes, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Communications The Open University Milton Keynes, UK","institution_ids":["https://openalex.org/I204136569"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111945998","display_name":"Alistair Willis","orcid":null},"institutions":[{"id":"https://openalex.org/I204136569","display_name":"The Open University","ror":"https://ror.org/05mzfcs16","country_code":"GB","type":"education","lineage":["https://openalex.org/I204136569"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alistair Willis","raw_affiliation_strings":["School of Computing and Communications The Open University Milton Keynes, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Communications The Open University Milton Keynes, UK","institution_ids":["https://openalex.org/I204136569"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204136569"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"344","last_page":"354"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9983999729156494,"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/T12031","display_name":"Speech and dialogue systems","score":0.996399998664856,"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/reliability","display_name":"Reliability (semiconductor)","score":0.8087142705917358},{"id":"https://openalex.org/keywords/plea","display_name":"Plea","score":0.6262799501419067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5753214359283447},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.5651552677154541},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.469426691532135},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.46605950593948364},{"id":"https://openalex.org/keywords/agreement","display_name":"Agreement","score":0.4525921642780304},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.44291743636131287},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3335411846637726},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3220323324203491},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2781296670436859},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.17017602920532227},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1523999571800232},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.12745821475982666},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.093182772397995},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.0832386314868927}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.8087142705917358},{"id":"https://openalex.org/C2777886440","wikidata":"https://www.wikidata.org/wiki/Q15916459","display_name":"Plea","level":2,"score":0.6262799501419067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5753214359283447},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5651552677154541},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.469426691532135},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.46605950593948364},{"id":"https://openalex.org/C2776818064","wikidata":"https://www.wikidata.org/wiki/Q829903","display_name":"Agreement","level":2,"score":0.4525921642780304},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.44291743636131287},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3335411846637726},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3220323324203491},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2781296670436859},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.17017602920532227},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1523999571800232},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.12745821475982666},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.093182772397995},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0832386314868927},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w19-8642","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8642","pdf_url":"https://www.aclweb.org/anthology/W19-8642.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 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},{"id":"pmh:oai:oro.open.ac.uk:67962","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196284","display_name":"Open Research Online - ORO (The Open University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I204136569","host_organization_name":"The Open University","host_organization_lineage":["https://openalex.org/I204136569"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-8642","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-8642","pdf_url":"https://www.aclweb.org/anthology/W19-8642.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 12th International Conference on Natural Language Generation","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2990787438.pdf","grobid_xml":"https://content.openalex.org/works/W2990787438.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W570266825","https://openalex.org/W1555380324","https://openalex.org/W1594247117","https://openalex.org/W1968667761","https://openalex.org/W1975879668","https://openalex.org/W1990657980","https://openalex.org/W2002664886","https://openalex.org/W2012378416","https://openalex.org/W2050256879","https://openalex.org/W2053154970","https://openalex.org/W2069378996","https://openalex.org/W2084105614","https://openalex.org/W2086059573","https://openalex.org/W2107031757","https://openalex.org/W2109600226","https://openalex.org/W2128856065","https://openalex.org/W2131915193","https://openalex.org/W2136202293","https://openalex.org/W2141766660","https://openalex.org/W2153222072","https://openalex.org/W2153804780","https://openalex.org/W2159306398","https://openalex.org/W2160375265","https://openalex.org/W2161318349","https://openalex.org/W2163329495","https://openalex.org/W2164777277","https://openalex.org/W2287528930","https://openalex.org/W2328886022","https://openalex.org/W2501011868","https://openalex.org/W2510483258","https://openalex.org/W2558224492","https://openalex.org/W2604799547","https://openalex.org/W2626407095","https://openalex.org/W2806532810","https://openalex.org/W2842624112","https://openalex.org/W2902583760","https://openalex.org/W2954116503","https://openalex.org/W2963748441","https://openalex.org/W2963903950","https://openalex.org/W4205597937","https://openalex.org/W4206474425","https://openalex.org/W4232519079","https://openalex.org/W4243989635","https://openalex.org/W4248679347","https://openalex.org/W4251971396","https://openalex.org/W4293257135","https://openalex.org/W4300870773"],"related_works":["https://openalex.org/W2014032021","https://openalex.org/W2036621849","https://openalex.org/W2330569546","https://openalex.org/W2350260616","https://openalex.org/W2351944896","https://openalex.org/W2500215510","https://openalex.org/W2370955712","https://openalex.org/W2485167466","https://openalex.org/W2045593234","https://openalex.org/W3159118406"],"abstract_inverted_index":{"Inter-Annotator":[0],"Agreement":[1],"(IAA)":[2],"is":[3,130],"used":[4,117],"as":[5,90],"a":[6,121],"means":[7],"of":[8,12,24,57,87,108,124],"assessing":[9],"the":[10,42,85,91,125,133],"quality":[11],"NLG":[13],"evaluation":[14,59,96,107,126],"data,":[15],"in":[16,46],"particular,":[17],"its":[18],"reliability.":[19,97,128],"According":[20],"to":[21,119],"existing":[22],"scales":[23],"IAA":[25,89],"interpretationsee,":[26],"for":[27,94,105],"example,":[28],"Lommel":[29,66],"et":[30,67,71,76],"al.":[31,68,72,77],"(":[32,78],"We":[33],"confirmed":[34],"this":[35],"trend":[36],"by":[37],"analysing":[38],"papers":[39,52],"published":[40],"over":[41],"last":[43],"10":[44],"years":[45],"NLG-specific":[47],"conferences":[48],"(in":[49],"total":[50],"135":[51],"that":[53,104],"included":[54],"some":[55],"sort":[56],"human":[58,99,106],"study).":[60],"Following":[61],"Sampson":[62],"and":[63,74,112],"Babarczy":[64],"(2008),":[65],"(2014),":[69],"Joshi":[70],"(2016)":[73],"Amidei":[75],"Using":[79],"three":[80,134],"case":[81,135],"studies,":[82],"we":[83,102],"show":[84],"limits":[86],"considering":[88],"only":[92],"criterion":[93],"checking":[95],"Given":[98],"language":[100],"variability,":[101],"propose":[103],"NLG,":[109],"correlation":[110],"coefficients":[111,114],"agreement":[113],"should":[115],"be":[116],"together":[118],"obtain":[120],"better":[122],"assessment":[123],"data":[127],"This":[129],"illustrated":[131],"using":[132],"studies.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
