{"id":"https://openalex.org/W2963677523","doi":"https://doi.org/10.18653/v1/d16-1062","title":"Building an Evaluation Scale using Item Response Theory","display_name":"Building an Evaluation Scale using Item Response Theory","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2963677523","doi":"https://doi.org/10.18653/v1/d16-1062","mag":"2963677523","pmid":"https://pubmed.ncbi.nlm.nih.gov/28004039","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/5167538"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d16-1062","doi":"https://doi.org/10.18653/v1/d16-1062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1062","pdf_url":"https://www.aclweb.org/anthology/D16-1062.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 2016 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.aclweb.org/anthology/D16-1062.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033125725","display_name":"John Patrick Lalor","orcid":"https://orcid.org/0000-0003-0848-4786","observed_orcids":["https://orcid.org/0000-0003-0848-4786"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Lalor","raw_affiliation_strings":["University of Massachusetts, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074969115","display_name":"Hao Wu","orcid":"https://orcid.org/0000-0001-6471-1774","observed_orcids":["https://orcid.org/0000-0001-6471-1774","https://orcid.org/0009-0001-2877-2470"]},"institutions":[{"id":"https://openalex.org/I103531236","display_name":"Boston College","ror":"https://ror.org/02n2fzt79","country_code":"US","type":"education","lineage":["https://openalex.org/I103531236"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wu","raw_affiliation_strings":["Boston College, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston College, MA, USA","institution_ids":["https://openalex.org/I103531236"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017601806","display_name":"Hong Qing Yu","orcid":"https://orcid.org/0000-0001-9263-5035","observed_orcids":["https://orcid.org/0000-0001-9263-5035"]},"institutions":[{"id":"https://openalex.org/I2800300635","display_name":"Edith Nourse Rogers Memorial Veterans Hospital","ror":"https://ror.org/015nymp25","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I2800300635","https://openalex.org/I4210095851"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"hong yu","raw_affiliation_strings":["University of Massachusetts, MA, USA; Bedford VAMC and CHOIR, MA, USA","Bedford VAMC and CHOIR, MA, USA","University of Massachusetts, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, MA, USA; Bedford VAMC and CHOIR, MA, USA","institution_ids":["https://openalex.org/I2800300635"]},{"raw_affiliation_string":"Bedford VAMC and CHOIR, MA, USA","institution_ids":["https://openalex.org/I2800300635"]},{"raw_affiliation_string":"University of Massachusetts, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3004,"has_fulltext":true,"cited_by_count":85,"citation_normalized_percentile":{"value":0.85756962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"2016","issue":null,"first_page":"648","last_page":"657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6815999746322632,"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":0.6815999746322632,"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/T10467","display_name":"Psychometric Methodologies and Testing","score":0.15440000593662262,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.039900001138448715,"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/item-response-theory","display_name":"item response theory","score":0.8619999885559082},{"id":"https://openalex.org/keywords/natural-language-inference","display_name":"natural language inference","score":0.9710000157356262},{"id":"https://openalex.org/keywords/item-difficulty","display_name":"item difficulty","score":0.8399999737739563},{"id":"https://openalex.org/keywords/item-discrimination","display_name":"item discrimination","score":0.7680000066757202},{"id":"https://openalex.org/keywords/psychometrics","display_name":"psychometrics","score":0.6610000133514404}],"concepts":[{"id":"https://openalex.org/C19875794","wikidata":"https://www.wikidata.org/wiki/Q1207340","display_name":"Item response theory","level":3,"score":0.6314305067062378},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5662054419517517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5598195791244507},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14423075318336487},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12896904349327087},{"id":"https://openalex.org/C171606756","wikidata":"https://www.wikidata.org/wiki/Q506132","display_name":"Psychometrics","level":2,"score":0.10351225733757019},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0845460593700409},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/d16-1062","doi":"https://doi.org/10.18653/v1/d16-1062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1062","pdf_url":"https://www.aclweb.org/anthology/D16-1062.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 2016 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmid:28004039","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28004039","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,"listed_in":[],"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":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:5167538","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5167538","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proc Conf Empir Methods Nat Lang Process","raw_type":"Text"},{"id":"pmh:oai:arXiv.org:1605.08889","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1605.08889","pdf_url":"https://arxiv.org/pdf/1605.08889","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":"doi:10.48550/arxiv.1605.08889","doi":"https://doi.org/10.48550/arxiv.1605.08889","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1605.08889","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/d16-1062","doi":"https://doi.org/10.18653/v1/d16-1062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d16-1062","pdf_url":"https://www.aclweb.org/anthology/D16-1062.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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 2016 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1152948468","display_name":"EHR Anticoagulants Pharmacovigilance","funder_award_id":"R01HL125089","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G4123628861","display_name":null,"funder_award_id":"I01 HX001457","funder_id":"https://openalex.org/F4320306127","funder_display_name":"U.S. Department of Veterans Affairs"},{"id":"https://openalex.org/G4427878829","display_name":"Resource Curation and Evaluation for EHR Note Comprehension","funder_award_id":"R01LM012817","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"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"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963677523.pdf","grobid_xml":"https://content.openalex.org/works/W2963677523.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W806995027","https://openalex.org/W1840435438","https://openalex.org/W1971410477","https://openalex.org/W2017966270","https://openalex.org/W2034108143","https://openalex.org/W2044780707","https://openalex.org/W2128669672","https://openalex.org/W2130158090","https://openalex.org/W2139338900","https://openalex.org/W2144934730","https://openalex.org/W2146007434","https://openalex.org/W2150098611","https://openalex.org/W2154299075","https://openalex.org/W2171278097","https://openalex.org/W2185175083","https://openalex.org/W2250307601","https://openalex.org/W2250318405","https://openalex.org/W2250482657","https://openalex.org/W2250790822","https://openalex.org/W2251089262","https://openalex.org/W2251818274","https://openalex.org/W2251919380","https://openalex.org/W2257979135","https://openalex.org/W2525127255","https://openalex.org/W2889272830","https://openalex.org/W2911296969","https://openalex.org/W2953084091","https://openalex.org/W2963869850","https://openalex.org/W4399569540"],"related_works":["https://openalex.org/W2419101866","https://openalex.org/W2970184386","https://openalex.org/W7154627663","https://openalex.org/W2990527403","https://openalex.org/W4415590663","https://openalex.org/W3013714087","https://openalex.org/W3110131742","https://openalex.org/W7169611917","https://openalex.org/W1519739771","https://openalex.org/W3125966950"],"abstract_inverted_index":{"Evaluation":[0],"of":[1,65,84,114],"NLP":[2,56,91,129],"methods":[3],"requires":[4],"testing":[5],"against":[6],"a":[7,26,101,111,135,155,163],"previously":[8],"vetted":[9],"gold-standard":[10,52,102],"test":[11,28,103],"set":[12,29,104],"and":[13,36,55,71,75,117,138,173],"reporting":[14],"standard":[15,149],"metrics":[16],"(accuracy/precision/recall/F1).":[17],"The":[18],"current":[19],"assumption":[20],"is":[21,60,139],"that":[22,124,154],"all":[23],"items":[24,67],"in":[25,81,134],"given":[27],"are":[30],"equal":[31],"with":[32,131],"regards":[33],"to":[34,62,141],"difficulty":[35,70],"discriminating":[37,72],"power.":[38],"We":[39,152],"propose":[40],"Item":[41],"Response":[42],"Theory":[43],"(IRT)":[44],"from":[45],"psychometrics":[46],"as":[47],"an":[48,90],"alternative":[49],"means":[50],"for":[51,78,89,105],"test-set":[53],"generation":[54],"system":[57,146],"evaluation.":[58],"IRT":[59,98,120,126,165],"able":[61,140],"describe":[63],"characteristics":[64,80,172],"individual":[66],"-":[68,74],"their":[69],"power":[73],"can":[76],"account":[77],"these":[79],"its":[82],"estimation":[83],"human":[85,115,136],"intelligence":[86],"or":[87],"ability":[88],"task.":[92],"In":[93],"this":[94],"paper,":[95],"we":[96,122],"demonstrate":[97],"by":[99],"generating":[100],"Recognizing":[106],"Textual":[107],"Entailment.":[108],"By":[109],"collecting":[110],"large":[112],"number":[113],"responses":[116],"fitting":[118],"our":[119,125],"model,":[121],"show":[123,153],"model":[127],"compares":[128],"systems":[130],"the":[132,170,174],"performance":[133,147],"population":[137],"provide":[142],"more":[143],"insight":[144],"into":[145],"than":[148],"evaluation":[150],"metrics.":[151],"high":[156,164],"accuracy":[157],"score":[158],"does":[159],"not":[160],"always":[161],"imply":[162],"score,":[166],"which":[167],"depends":[168],"on":[169],"item":[171],"response":[175],"pattern.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-07-30T00:00:00"}