{"id":"https://openalex.org/W2891340257","doi":"https://doi.org/10.18653/v1/d18-1500","title":"Understanding Deep Learning Performance through an Examination of Test Set Difficulty: A Psychometric Case Study","display_name":"Understanding Deep Learning Performance through an Examination of Test Set Difficulty: A Psychometric Case Study","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2891340257","doi":"https://doi.org/10.18653/v1/d18-1500","mag":"2891340257","pmid":"https://pubmed.ncbi.nlm.nih.gov/33241233"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1500","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1500","pdf_url":"https://www.aclweb.org/anthology/D18-1500.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1500.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033125725","display_name":"John P. Lalor","orcid":"https://orcid.org/0000-0003-0848-4786"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Lalor","raw_affiliation_strings":["College of Information and Computer Sciences, University of Massachusetts, Amherst"],"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074969115","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0001-6471-1774"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["Department of Psychology and Human Development, Vanderbilt University"],"affiliations":[{"raw_affiliation_string":"Department of Psychology and Human Development, Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062473985","display_name":"Tsendsuren Munkhdalai","orcid":"https://orcid.org/0000-0002-8783-4993"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I4402554038","display_name":"Microsoft Research Montr\u00e9al (Canada)","ror":"https://ror.org/05xdft911","country_code":null,"type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4402554038"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tsendsuren Munkhdalai","raw_affiliation_strings":["Microsoft Research, Montr\u00e9al, Qu\u00e9bec"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Montr\u00e9al, Qu\u00e9bec","institution_ids":["https://openalex.org/I4210164937","https://openalex.org/I4402554038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017601806","display_name":"Hong Yu","orcid":"https://orcid.org/0000-0001-9263-5035"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]},{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Yu","raw_affiliation_strings":["College of Information and Computer Sciences, University of Massachusetts, Amherst","Department of Computer Science, University of Massachusetts, Lowell"],"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"Department of Computer Science, University of Massachusetts, Lowell","institution_ids":["https://openalex.org/I133738476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033125725"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":2.6061,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92063019,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2018","issue":null,"first_page":"4711","last_page":"4716"},"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":0.9872999787330627,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.758840799331665},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6902102828025818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6776459217071533},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6689510345458984},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.6174901127815247},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5710573196411133},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5301205515861511},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5180161595344543},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5131471753120422},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4689815640449524},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4335757791996002},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.340928852558136},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2572895288467407},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09954935312271118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758840799331665},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6902102828025818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6776459217071533},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6689510345458984},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.6174901127815247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5710573196411133},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5301205515861511},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5180161595344543},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5131471753120422},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4689815640449524},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4335757791996002},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.340928852558136},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2572895288467407},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09954935312271118},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/d18-1500","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1500","pdf_url":"https://www.aclweb.org/anthology/D18-1500.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmid:33241233","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33241233","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:7685075","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7685075","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc Conf Empir Methods Nat Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1500","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1500","pdf_url":"https://www.aclweb.org/anthology/D18-1500.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8799999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306127","display_name":"U.S. Department of Veterans Affairs","ror":"https://ror.org/05rsv9s98"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2891340257.pdf","grobid_xml":"https://content.openalex.org/works/W2891340257.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W59378016","https://openalex.org/W1825499807","https://openalex.org/W1832693441","https://openalex.org/W1840435438","https://openalex.org/W1974475215","https://openalex.org/W2017966270","https://openalex.org/W2064675550","https://openalex.org/W2073375062","https://openalex.org/W2114168642","https://openalex.org/W2128669672","https://openalex.org/W2164777277","https://openalex.org/W2251818274","https://openalex.org/W2251939518","https://openalex.org/W2295951612","https://openalex.org/W2296073425","https://openalex.org/W2572405493","https://openalex.org/W2798100162","https://openalex.org/W2798235027","https://openalex.org/W2889272830","https://openalex.org/W2962736243","https://openalex.org/W2962843521","https://openalex.org/W2963120843","https://openalex.org/W2963305465","https://openalex.org/W2963488527","https://openalex.org/W2963677523","https://openalex.org/W2963973721","https://openalex.org/W3003519915","https://openalex.org/W4301152280","https://openalex.org/W4399569540"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W3099765033","https://openalex.org/W2997155179","https://openalex.org/W4387327236","https://openalex.org/W2183488467","https://openalex.org/W1990237101","https://openalex.org/W4309907966","https://openalex.org/W4387896287","https://openalex.org/W2187490799","https://openalex.org/W3170838353"],"abstract_inverted_index":{"Interpreting":[0],"the":[1,33,75,85],"performance":[2],"of":[3,14,35,77],"deep":[4],"learning":[5],"models":[6],"beyond":[7],"test":[8,37],"set":[9,38],"accuracy":[10],"is":[11,28,45,82],"challenging.":[12],"Characteristics":[13],"individual":[15],"data":[16,26],"points":[17],"are":[18,90,97],"often":[19],"not":[20],"considered":[21],"during":[22],"evaluation,":[23],"and":[24,50,69],"each":[25],"point":[27],"treated":[29],"equally.":[30],"We":[31,52],"examine":[32],"impact":[34],"a":[36,46,79],"question's":[39,86],"difficulty":[40,49,54],"to":[41],"determine":[42],"if":[43],"there":[44],"relationship":[47],"between":[48],"performance.":[51],"model":[53],"using":[55],"well-studied":[56],"psychometric":[57],"methods":[58],"on":[59,64],"human":[60],"response":[61],"patterns.":[62],"Experiments":[63],"Natural":[65],"Language":[66],"Inference":[67],"(NLI)":[68],"Sentiment":[70],"Analysis":[71],"(SA)":[72],"show":[73],"that":[74],"likelihood":[76],"answering":[78],"question":[80],"correctly":[81],"impacted":[83],"by":[84],"difficulty.":[87],"As":[88],"DNNs":[89],"trained":[91],"with":[92],"more":[93,99],"data,":[94],"easy":[95],"examples":[96],"learned":[98],"quickly":[100],"than":[101],"hard":[102],"examples.":[103]},"counts_by_year":[{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}