{"id":"https://openalex.org/W3153923402","doi":"https://doi.org/10.48550/arxiv.2104.05361","title":"The Great Misalignment Problem in Human Evaluation of NLP Methods","display_name":"The Great Misalignment Problem in Human Evaluation of NLP Methods","publication_year":2021,"publication_date":"2021-04-12","ids":{"openalex":"https://openalex.org/W3153923402","doi":"https://doi.org/10.48550/arxiv.2104.05361","mag":"3153923402"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2104.05361","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.05361","pdf_url":"https://arxiv.org/pdf/2104.05361","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.05361","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002214613","display_name":"Mika K H\u00e4m\u00e4l\u00e4inen","orcid":"https://orcid.org/0000-0001-9315-1278","observed_orcids":["https://orcid.org/0000-0001-9315-1278"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H\u00e4m\u00e4l\u00e4inen, Mika","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057148063","display_name":"Khalid Alnajjar","orcid":"https://orcid.org/0000-0002-7986-2994","observed_orcids":["https://orcid.org/0000-0002-7986-2994"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alnajjar, Khalid","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":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6610999703407288,"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":0.6610999703407288,"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":0.2053000032901764,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.025299999862909317,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/human-evaluation","display_name":"human evaluation","score":0.8370000123977661},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.6639999747276306},{"id":"https://openalex.org/keywords/problem-formulation","display_name":"problem formulation","score":0.8500000238418579},{"id":"https://openalex.org/keywords/evaluation-methodology","display_name":"evaluation methodology","score":0.628000020980835},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.796999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6846920251846313},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.6452687978744507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343994498252869},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.4398556649684906},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4069894850254059},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38216057419776917},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11983665823936462},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10669103264808655},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.08706367015838623},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2104.05361","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.05361","pdf_url":"https://arxiv.org/pdf/2104.05361","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,"listed_in":[],"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":"pmh:oai:helda.helsinki.fi:10138/330174","doi":null,"is_oa":true,"landing_page_url":"https://www.aclweb.org/anthology/2021.humeval-1.8","pdf_url":"http://hdl.handle.net/10138/330174","source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},{"id":"doi:10.48550/arxiv.2104.05361","doi":"https://doi.org/10.48550/arxiv.2104.05361","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.05361","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,"listed_in":[],"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"},{"id":"mag:3155063497","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2104.05361","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,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.05361","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.05361","pdf_url":"https://arxiv.org/pdf/2104.05361","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,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.6399999856948853}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W640637620","https://openalex.org/W2101105183","https://openalex.org/W2563072008","https://openalex.org/W2737041661","https://openalex.org/W2806532810","https://openalex.org/W2889666157","https://openalex.org/W3034330464","https://openalex.org/W3147657411","https://openalex.org/W3159794114"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"We":[0,40],"outline":[1],"the":[2,15,23,27,35,38,96,102,113],"Great":[3,103],"Misalignment":[4,104],"Problem":[5,105],"in":[6,20,32,52,70,72,89,95],"natural":[7],"language":[8],"processing":[9],"research,":[10],"this":[11,42],"means":[12],"simply":[13],"that":[14,55,64,87,101],"problem":[16,44,75],"definition":[17,36],"is":[18,30,106],"not":[19,31],"line":[21,33,71,90],"with":[22,34,58,91],"method":[24,77],"proposed":[25],"and":[26,78,110,115],"human":[28,59,85,122],"evaluation":[29,86],"nor":[37],"method.":[39,97],"study":[41],"misalignment":[43],"by":[45,120],"surveying":[46],"10":[47],"randomly":[48],"sampled":[49],"papers":[50,82],"published":[51],"ACL":[53],"2020":[54],"report":[56],"results":[57,62,99,118],"evaluation.":[60,79,123],"Our":[61],"show":[63],"only":[65],"one":[66,109],"paper":[67],"was":[68,88,93],"fully":[69],"terms":[73],"of":[74,117],"definition,":[76],"Only":[80],"two":[81],"presented":[83],"a":[84,107,121],"what":[92],"modeled":[94],"These":[98],"highlight":[100],"major":[108],"it":[111],"affects":[112],"validity":[114],"reproducibility":[116],"obtained":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2021-04-26T00:00:00"}