{"id":"https://openalex.org/W3211758383","doi":"https://doi.org/10.1162/tacl_a_00417","title":"A Statistical Analysis of Summarization Evaluation Metrics Using Resampling Methods","display_name":"A Statistical Analysis of Summarization Evaluation Metrics Using Resampling Methods","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3211758383","doi":"https://doi.org/10.1162/tacl_a_00417","mag":"3211758383"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00417","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00417","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00417/1970948/tacl_a_00417.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00417/1970948/tacl_a_00417.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007708364","display_name":"Daniel Deutsch","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Deutsch","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania, USA. ddeutsch@seas.upenn.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania, USA. ddeutsch@seas.upenn.edu","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089112142","display_name":"Rotem Dror","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rotem Dror","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania, USA. rtmdrr@seas.upenn.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania, USA. rtmdrr@seas.upenn.edu","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023802054","display_name":"Dan Roth","orcid":"https://orcid.org/0009-0002-1447-5173"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dan Roth","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania, USA. danroth@seas.upenn.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania, USA. danroth@seas.upenn.edu","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007708364","https://openalex.org/A5023802054","https://openalex.org/A5089112142"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":4.2906,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.95103226,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"9","issue":null,"first_page":"1132","last_page":"1146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T13083","display_name":"Advanced Text Analysis 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"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8932466506958008},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.8289105296134949},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.8155699968338013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8143881559371948},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7061049342155457},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5328023433685303},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4837929904460907},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4822726845741272},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46029600501060486},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.4517662823200226},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.4516141712665558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43025490641593933},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.414204478263855},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3425743579864502},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.14289143681526184},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1422199010848999}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8932466506958008},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.8289105296134949},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.8155699968338013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143881559371948},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7061049342155457},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5328023433685303},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4837929904460907},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4822726845741272},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46029600501060486},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.4517662823200226},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.4516141712665558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43025490641593933},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.414204478263855},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3425743579864502},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.14289143681526184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1422199010848999},{"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00417","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00417","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00417/1970948/tacl_a_00417.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:47670c82edb34081a75876b16702b04a","is_oa":false,"landing_page_url":"https://doaj.org/article/47670c82edb34081a75876b16702b04a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 9, Pp 1132-1146 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00417","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00417","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00417/1970948/tacl_a_00417.pdf","source":{"id":"https://openalex.org/S2729999759","display_name":"Transactions of the Association for Computational Linguistics","issn_l":"2307-387X","issn":["2307-387X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Association for Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1472423617","display_name":null,"funder_award_id":"FA8750-19-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G638997368","display_name":null,"funder_award_id":"2019-19051600006","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320337349","display_name":"NIH Office of the Director","ror":"https://ror.org/00fj8a872"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3211758383.pdf","grobid_xml":"https://content.openalex.org/works/W3211758383.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W200488758","https://openalex.org/W1533179050","https://openalex.org/W1554540371","https://openalex.org/W1995945562","https://openalex.org/W2030332904","https://openalex.org/W2033582154","https://openalex.org/W2034562813","https://openalex.org/W2049835150","https://openalex.org/W2079361112","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2142078760","https://openalex.org/W2168745915","https://openalex.org/W2182572585","https://openalex.org/W2250234233","https://openalex.org/W2251023345","https://openalex.org/W2316643298","https://openalex.org/W2758374095","https://openalex.org/W2759181158","https://openalex.org/W2798935874","https://openalex.org/W2938002492","https://openalex.org/W2963583956","https://openalex.org/W2963929190","https://openalex.org/W2970785793","https://openalex.org/W2970791445","https://openalex.org/W3014784959","https://openalex.org/W3022131377","https://openalex.org/W3034360475","https://openalex.org/W3045153201","https://openalex.org/W3047398590","https://openalex.org/W3101017384","https://openalex.org/W3105678454","https://openalex.org/W3119878165","https://openalex.org/W3159259047","https://openalex.org/W3191640844","https://openalex.org/W4229977739","https://openalex.org/W6631167871","https://openalex.org/W6680615738","https://openalex.org/W6686204840","https://openalex.org/W6691492844","https://openalex.org/W6691642095","https://openalex.org/W6703902474","https://openalex.org/W6712362004","https://openalex.org/W6712973960","https://openalex.org/W6761205521","https://openalex.org/W6784157648","https://openalex.org/W6788156848"],"related_works":["https://openalex.org/W2021333301","https://openalex.org/W2375771286","https://openalex.org/W69222743","https://openalex.org/W4246719347","https://openalex.org/W2077508419","https://openalex.org/W2006114390","https://openalex.org/W1913467779","https://openalex.org/W4229900761","https://openalex.org/W2380800094","https://openalex.org/W2149345204"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"quality":[2],"of":[3,24,86,103,116,134],"a":[4,21,44],"summarization":[5,94],"evaluation":[6,111,158],"metric":[7],"is":[8,28,50,90],"quantified":[9],"by":[10,63],"calculating":[11,67],"the":[12,87,101,122,132],"correlation":[13,33],"between":[14,39],"its":[15],"scores":[16],"and":[17,70,81,152],"human":[18,117],"annotations":[19],"across":[20,113],"large":[22],"number":[23],"summaries.":[25],"Currently,":[26],"it":[27,49],"unclear":[29],"how":[30],"precise":[31],"these":[32,60,105],"estimates":[34],"are,":[35],"nor":[36],"whether":[37],"differences":[38],"two":[40,61,77,96,148],"metrics\u2019":[41],"correlations":[42,75],"reflect":[43],"true":[45],"difference":[46],"or":[47],"if":[48],"due":[51],"to":[52,107,142],"mere":[53],"chance.":[54],"In":[55],"this":[56],"work,":[57],"we":[58,99],"address":[59],"problems":[62],"proposing":[64],"methods":[65,89,106],"for":[66,74,93],"confidence":[68,123],"intervals":[69,124],"running":[71],"hypothesis":[72],"tests":[73],"using":[76],"resampling":[78],"methods,":[79],"bootstrapping":[80],"permutation.":[82],"After":[83],"evaluating":[84],"which":[85],"proposed":[88],"most":[91],"appropriate":[92],"through":[95],"simulation":[97],"experiments,":[98],"analyze":[100],"results":[102],"applying":[104],"several":[108],"different":[109],"automatic":[110,135],"metrics":[112,140],"three":[114],"sets":[115],"annotations.":[118],"We":[119],"find":[120],"that":[121],"are":[125],"rather":[126],"wide,":[127],"demonstrating":[128],"high":[129],"uncertainty":[130],"in":[131,156],"reliability":[133],"metrics.":[136],"Further,":[137],"although":[138],"many":[139],"fail":[141],"show":[143],"statistical":[144],"improvements":[145],"over":[146],"ROUGE,":[147],"recent":[149],"works,":[150],"QAEval":[151],"BERTScore,":[153],"do":[154],"so":[155],"some":[157],"settings.1":[159]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}