{"id":"https://openalex.org/W3201300710","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.575","title":"Perturbation CheckLists for Evaluating NLG Evaluation Metrics","display_name":"Perturbation CheckLists for Evaluating NLG Evaluation Metrics","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3201300710","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.575","mag":"3201300710"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.emnlp-main.575","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.575","pdf_url":"https://aclanthology.org/2021.emnlp-main.575.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2021.emnlp-main.575.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087678154","display_name":"Ananya B. Sai","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ananya B. Sai","raw_affiliation_strings":["Indian Institute of Technology, Madras","Robert Bosch Centre for Data Science and Artificial Intelligence, IIT Madras"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Robert Bosch Centre for Data Science and Artificial Intelligence, IIT Madras","institution_ids":["https://openalex.org/I4210151956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073080117","display_name":"Tanay Dixit","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanay Dixit","raw_affiliation_strings":["Indian Institute of Technology, Madras"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013711594","display_name":"Dev Yashpal Sheth","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dev Yashpal Sheth","raw_affiliation_strings":["Indian Institute of Technology, Madras","Robert Bosch Centre for Data Science and Artificial Intelligence, IIT Madras"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Robert Bosch Centre for Data Science and Artificial Intelligence, IIT Madras","institution_ids":["https://openalex.org/I4210151956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101680754","display_name":"Sreyas Mohan","orcid":"https://orcid.org/0000-0001-8629-0181"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreyas Mohan","raw_affiliation_strings":["Center for Data Science, New York University"],"affiliations":[{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050036814","display_name":"Mitesh M. Khapra","orcid":"https://orcid.org/0009-0008-3687-9922"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]},{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mitesh M. Khapra","raw_affiliation_strings":["Indian Institute of Technology, Madras","AI4Bharat","Robert Bosch Centre for Data Science and Artificial Intelligence, IIT Madras"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Madras","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"AI4Bharat","institution_ids":[]},{"raw_affiliation_string":"Robert Bosch Centre for Data Science and Artificial Intelligence, IIT Madras","institution_ids":["https://openalex.org/I4210151956"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087678154"],"corresponding_institution_ids":["https://openalex.org/I24676775","https://openalex.org/I4210151956"],"apc_list":null,"apc_paid":null,"fwci":3.6817,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94585605,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7219","last_page":"7234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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":0.9850000143051147,"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/computer-science","display_name":"Computer science","score":0.7904036045074463},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.7023923397064209},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.6955398321151733},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6403684020042419},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.5684136748313904},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.551816463470459},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4591066837310791},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44039639830589294},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4366164207458496},{"id":"https://openalex.org/keywords/evaluation-methods","display_name":"Evaluation methods","score":0.4214906692504883},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41516441106796265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3655482530593872},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.24812030792236328},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.14893561601638794},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14297080039978027},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08717265725135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904036045074463},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.7023923397064209},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.6955398321151733},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6403684020042419},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.5684136748313904},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.551816463470459},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4591066837310791},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44039639830589294},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4366164207458496},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.4214906692504883},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41516441106796265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3655482530593872},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.24812030792236328},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.14893561601638794},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14297080039978027},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08717265725135803},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2021.emnlp-main.575","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.575","pdf_url":"https://aclanthology.org/2021.emnlp-main.575.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.emnlp-main.575","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.575","pdf_url":"https://aclanthology.org/2021.emnlp-main.575.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[{"id":"https://openalex.org/G1780723959","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320322211","funder_display_name":"Indian Institute of Technology Madras"}],"funders":[{"id":"https://openalex.org/F4320322211","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3201300710.pdf","grobid_xml":"https://content.openalex.org/works/W3201300710.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1489525520","https://openalex.org/W1983578042","https://openalex.org/W2093790824","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2147192413","https://openalex.org/W2149327368","https://openalex.org/W2154652894","https://openalex.org/W2226480163","https://openalex.org/W2250645967","https://openalex.org/W2251610689","https://openalex.org/W2506483933","https://openalex.org/W2584220694","https://openalex.org/W2729046720","https://openalex.org/W2741606601","https://openalex.org/W2758950307","https://openalex.org/W2794365787","https://openalex.org/W2806532810","https://openalex.org/W2888812214","https://openalex.org/W2904443424","https://openalex.org/W2916772188","https://openalex.org/W2947771965","https://openalex.org/W2952523122","https://openalex.org/W2962764348","https://openalex.org/W2963527228","https://openalex.org/W2963748441","https://openalex.org/W2963903950","https://openalex.org/W2965373594","https://openalex.org/W2970858040","https://openalex.org/W2971034336","https://openalex.org/W2971094522","https://openalex.org/W3035252911","https://openalex.org/W3035408261","https://openalex.org/W3035507081","https://openalex.org/W3035628162","https://openalex.org/W3035656139","https://openalex.org/W3037013468","https://openalex.org/W3098358988","https://openalex.org/W3098968529","https://openalex.org/W3104405162","https://openalex.org/W3105424285","https://openalex.org/W3109862485","https://openalex.org/W3117574848","https://openalex.org/W3131933120","https://openalex.org/W3159259047","https://openalex.org/W3159892921","https://openalex.org/W3186655327","https://openalex.org/W4287684343"],"related_works":["https://openalex.org/W2365169615","https://openalex.org/W1970538215","https://openalex.org/W2400151637","https://openalex.org/W2975827637","https://openalex.org/W2354089692","https://openalex.org/W2121300814","https://openalex.org/W595497825","https://openalex.org/W4236323843","https://openalex.org/W4389519239","https://openalex.org/W4323651265"],"abstract_inverted_index":{"Natural":[0],"Language":[1],"Generation":[2],"(NLG)":[3],"evaluation":[4,36,81,112,121,154,191,223,235],"is":[5,49,103,126],"a":[6,50,97,163,218],"multifaceted":[7],"task":[8,64],"requiring":[9],"assessment":[10,220],"of":[11,65,77,155,221,236],"multiple":[12,40],"desirable":[13,138],"criteria,":[14,139],"e.g.,":[15],"fluency,":[16],"coherency,":[17],"coverage,":[18],"relevance,":[19],"adequacy,":[20],"overall":[21],"quality,":[22],"etc.":[23],"Across":[24],"existing":[25,190],"datasets":[26],"for":[27,62,83,96,140,150,217],"6":[28,115],"NLG":[29,84,142],"tasks,":[30],"we":[31,147],"observe":[32],"that":[33,73,87,124,173,189],"the":[34,63,74,170,174,184,209],"human":[35,55,134],"scores":[37,56,92,135,204],"on":[38,57,136],"these":[39],"criteria":[41,99,122,165,182],"are":[42,193],"often":[43],"not":[44,194],"correlated.":[45],"For":[46],"example,":[47],"there":[48,125],"very":[51],"low":[52],"correlation":[53],"between":[54],"fluency":[58],"and":[59,118,153,168,201,228,234],"data":[60,67],"coverage":[61,185],"structured":[66],"to":[68,208],"text":[69],"generation.":[70],"This":[71],"suggests":[72],"current":[75],"recipe":[76],"proposing":[78],"new":[79],"automatic":[80,111,156,222],"metrics":[82,113,192,224],"by":[85,94,206],"showing":[86],"they":[88],"correlate":[89],"well":[90,132],"with":[91,133,203],"assigned":[93,205],"humans":[95,207],"single":[98,128],"(overall":[100],"quality)":[101],"alone":[102],"inadequate.":[104],"Indeed,":[105],"our":[106],"extensive":[107],"study":[108],"involving":[109],"25":[110],"across":[114],"different":[116,120],"tasks":[117],"18":[119],"shows":[123],"no":[127],"metric":[129],"which":[130,161],"correlates":[131],"all":[137],"most":[141],"tasks.":[143],"Given":[144],"this":[145,180],"situation,":[146],"propose":[148],"CheckLists":[149],"better":[151,231],"design":[152,159],"metrics.":[157,238],"We":[158,187],"templates":[160,214],"target":[162],"specific":[164,181],"(e.g.,":[166,183],"coverage)":[167],"perturb":[169],"output":[171],"such":[172,198,237],"quality":[175],"gets":[176],"affected":[177],"only":[178],"along":[179],"drops).":[186],"show":[188],"robust":[195],"against":[196],"even":[197],"simple":[199],"perturbations":[200],"disagree":[202],"perturbed":[210],"output.":[211],"The":[212],"proposed":[213],"thus":[215],"allow":[216],"fine-grained":[219],"exposing":[225],"their":[226],"limitations":[227],"will":[229],"facilitate":[230],"design,":[232],"analysis":[233],"1":[239]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":6}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}