{"id":"https://openalex.org/W4404838894","doi":"https://doi.org/10.1142/s0218194025500032","title":"A Model-Based Evaluation Metric for Question Answering Systems","display_name":"A Model-Based Evaluation Metric for Question Answering Systems","publication_year":2024,"publication_date":"2024-11-29","ids":{"openalex":"https://openalex.org/W4404838894","doi":"https://doi.org/10.1142/s0218194025500032"},"language":"en","primary_location":{"id":"doi:10.1142/s0218194025500032","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194025500032","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082540555","display_name":"Dilan Bak\u0131r","orcid":"https://orcid.org/0000-0001-6650-6942"},"institutions":[{"id":"https://openalex.org/I4101805","display_name":"Y\u0131ld\u0131z Technical University","ror":"https://ror.org/0547yzj13","country_code":"TR","type":"education","lineage":["https://openalex.org/I4101805"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Dilan Bak\u0131r","raw_affiliation_strings":["Computer Engineering Department, Yildiz Technical University Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-6650-6942","affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Yildiz Technical University Istanbul, Turkey","institution_ids":["https://openalex.org/I4101805"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036873257","display_name":"Mehmet S. Akta\u015f","orcid":"https://orcid.org/0000-0001-7908-5067"},"institutions":[{"id":"https://openalex.org/I4101805","display_name":"Y\u0131ld\u0131z Technical University","ror":"https://ror.org/0547yzj13","country_code":"TR","type":"education","lineage":["https://openalex.org/I4101805"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mehmet S. Aktas","raw_affiliation_strings":["Computer Engineering Department, Yildiz Technical University Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-7908-5067","affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Yildiz Technical University Istanbul, Turkey","institution_ids":["https://openalex.org/I4101805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029440615","display_name":"Beytullah Yildiz","orcid":"https://orcid.org/0000-0001-7664-5145"},"institutions":[{"id":"https://openalex.org/I45542416","display_name":"Atilim University","ror":"https://ror.org/04pd3v454","country_code":"TR","type":"education","lineage":["https://openalex.org/I45542416"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Beytullah Y\u0131ld\u0131z","raw_affiliation_strings":["Software Engineering Department, Atilim University Ankara, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-7664-5145","affiliations":[{"raw_affiliation_string":"Software Engineering Department, Atilim University Ankara, Turkey","institution_ids":["https://openalex.org/I45542416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082540555"],"corresponding_institution_ids":["https://openalex.org/I4101805"],"apc_list":null,"apc_paid":null,"fwci":0.9441,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80709033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"35","issue":"02","first_page":"243","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9736999869346619,"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":0.9736999869346619,"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/T12031","display_name":"Speech and dialogue systems","score":0.9327999949455261,"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/question-answering","display_name":"Question answering","score":0.8260881900787354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6538857221603394},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6124567985534668},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5794496536254883},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3516060709953308},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1509365737438202}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8260881900787354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6538857221603394},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6124567985534668},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5794496536254883},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3516060709953308},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1509365737438202},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218194025500032","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194025500032","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W26885468","https://openalex.org/W1982951827","https://openalex.org/W2018242550","https://openalex.org/W2048106736","https://openalex.org/W2048878537","https://openalex.org/W2098561067","https://openalex.org/W2143539737","https://openalex.org/W2197992444","https://openalex.org/W2888302696","https://openalex.org/W2888812214","https://openalex.org/W2919548633","https://openalex.org/W2945760033","https://openalex.org/W2962972512","https://openalex.org/W2963748441","https://openalex.org/W2963903950","https://openalex.org/W2971034336","https://openalex.org/W2987624052","https://openalex.org/W3022685184","https://openalex.org/W3128893795","https://openalex.org/W3139038810","https://openalex.org/W3160426102","https://openalex.org/W3167021021","https://openalex.org/W3187063016","https://openalex.org/W3212260607","https://openalex.org/W4226327346","https://openalex.org/W4230407178","https://openalex.org/W4237389337","https://openalex.org/W4243609394","https://openalex.org/W4285590546","https://openalex.org/W4323266881","https://openalex.org/W4362734951","https://openalex.org/W4391097745","https://openalex.org/W4399439184","https://openalex.org/W4400157234"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912"],"abstract_inverted_index":{"The":[0,42,154,194],"paper":[1],"addresses":[2],"the":[3,50,55,65,74,105,175,207],"limitations":[4],"of":[5,57,67,76,177,183,209],"traditional":[6,108],"evaluation":[7,27,180,192],"metrics":[8,58,109],"for":[9,91,143,168,215],"Question":[10],"Answering":[11],"(QA)":[12],"systems":[13,146],"that":[14,104,197],"primarily":[15],"focus":[16],"on":[17,70,80],"syntax":[18,63],"and":[19,30,36,73,94,113,133,186,219],"n-gram":[20],"similarity.":[21],"We":[22],"propose":[23],"a":[24,32,141,164,178,202],"novel":[25],"model-based":[26,199],"metric,":[28],"MQA-metric,":[29],"create":[31],"human-judgment-based":[33],"dataset,":[34],"squad-qametric":[35],"marco-qametric,":[37],"to":[38,45,129],"validate":[39],"our":[40,198],"approach.":[41],"research":[43],"aims":[44],"solve":[46],"several":[47],"key":[48],"problems:":[49],"objectivity":[51],"in":[52,205],"dataset":[53,92],"labeling,":[54],"effectiveness":[56],"when":[59],"there":[60],"is":[61,213],"no":[62],"similarity,":[64],"impact":[66],"answer":[68,78],"length":[69],"metric":[71,81,156],"performance,":[72],"influence":[75],"real":[77],"quality":[79,208],"results.":[82],"To":[83],"tackle":[84],"these":[85],"challenges,":[86],"we":[87],"designed":[88],"an":[89,187],"interface":[90],"labeling":[93],"conducted":[95],"extensive":[96,188],"experiments":[97],"with":[98,159,190],"human":[99,160],"reviewers.":[100],"Our":[101,172],"analysis":[102],"shows":[103],"MQA-metric":[106,118],"outperforms":[107],"like":[110],"BLEU,":[111],"ROUGE":[112],"METEOR.":[114],"Unlike":[115],"existing":[116,191],"metrics,":[117],"leverages":[119],"semantic":[120,149],"comprehension":[121],"through":[122],"large":[123],"language":[124],"models":[125],"(LLMs),":[126],"enabling":[127],"it":[128,163],"capture":[130],"contextual":[131],"nuances":[132],"synonymous":[134],"expressions":[135],"more":[136,165],"effectively.":[137],"This":[138],"approach":[139,200],"sets":[140],"standard":[142],"evaluating":[144,169],"QA":[145,170,210],"by":[147],"prioritizing":[148],"accuracy":[150],"over":[151],"surface-level":[152],"similarities.":[153],"proposed":[155],"correlates":[157],"better":[158],"judgment,":[161],"making":[162],"reliable":[166],"tool":[167],"systems.":[171],"contributions":[173],"include":[174],"development":[176],"robust":[179],"workflow,":[181],"creation":[182],"high-quality":[184],"datasets,":[185],"comparison":[189],"methods.":[193],"results":[195],"indicate":[196],"provides":[201],"significant":[203],"improvement":[204],"assessing":[206],"systems,":[211],"which":[212],"crucial":[214],"their":[216],"practical":[217],"application":[218],"trustworthiness.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2024-11-29T00:00:00"}