{"id":"https://openalex.org/W4385859354","doi":"https://doi.org/10.1162/tacl_a_00590","title":"Cross-functional Analysis of Generalization in Behavioral Learning","display_name":"Cross-functional Analysis of Generalization in Behavioral Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385859354","doi":"https://doi.org/10.1162/tacl_a_00590"},"language":"en","primary_location":{"id":"doi:10.1162/tacl_a_00590","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00590","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00590/2154429/tacl_a_00590.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_00590/2154429/tacl_a_00590.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048725706","display_name":"Pedro Henrique Luz de Araujo","orcid":"https://orcid.org/0000-0002-6114-832X"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Pedro Henrique Luz de Araujo","raw_affiliation_strings":["Faculty of Computer Science, University of Vienna, Vienna, Austria","UniVie Doctoral School Computer Science, Vienna, Austria. pedro.henrique.luz.de.araujo@univie.ac.at"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]},{"raw_affiliation_string":"UniVie Doctoral School Computer Science, Vienna, Austria. pedro.henrique.luz.de.araujo@univie.ac.at","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046895021","display_name":"Benjamin Roth","orcid":"https://orcid.org/0000-0003-0362-0267"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Benjamin Roth","raw_affiliation_strings":["Faculty of Computer Science, University of Vienna, Vienna, Austria","Faculty of Philological and Cultural Studies, University of Vienna, Vienna, Austria. benjamin.roth@univie.ac.at"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]},{"raw_affiliation_string":"Faculty of Philological and Cultural Studies, University of Vienna, Vienna, Austria. benjamin.roth@univie.ac.at","institution_ids":["https://openalex.org/I129774422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046895021","https://openalex.org/A5048725706"],"corresponding_institution_ids":["https://openalex.org/I129774422"],"apc_list":null,"apc_paid":null,"fwci":0.6345,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73145763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"1066","last_page":"1081"},"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/T10260","display_name":"Software Engineering Research","score":0.9983999729156494,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830022573471069},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6878366470336914},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6852408647537231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6177545189857483},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6042139530181885},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5085312128067017},{"id":"https://openalex.org/keywords/test-suite","display_name":"Test suite","score":0.4903697967529297},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49027732014656067},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.42567750811576843},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32420867681503296},{"id":"https://openalex.org/keywords/test-case","display_name":"Test case","score":0.20616638660430908},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1282021403312683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830022573471069},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6878366470336914},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6852408647537231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6177545189857483},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6042139530181885},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5085312128067017},{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.4903697967529297},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49027732014656067},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.42567750811576843},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32420867681503296},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.20616638660430908},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1282021403312683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/tacl_a_00590","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00590","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00590/2154429/tacl_a_00590.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:08a134b2cab2421499773335120e819f","is_oa":true,"landing_page_url":"https://doaj.org/article/08a134b2cab2421499773335120e819f","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Transactions of the Association for Computational Linguistics, Vol 11 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/tacl_a_00590","is_oa":true,"landing_page_url":"https://doi.org/10.1162/tacl_a_00590","pdf_url":"https://direct.mit.edu/tacl/article-pdf/doi/10.1162/tacl_a_00590/2154429/tacl_a_00590.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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8799999952316284}],"awards":[{"id":"https://openalex.org/G5514542193","display_name":null,"funder_award_id":"10.47379/VRG19008","funder_id":"https://openalex.org/F4320321003","funder_display_name":"Vienna Science and Technology Fund"}],"funders":[{"id":"https://openalex.org/F4320321003","display_name":"Vienna Science and Technology Fund","ror":"https://ror.org/01f9mc681"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385859354.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2057399676","https://openalex.org/W2602856279","https://openalex.org/W2771472444","https://openalex.org/W2906152891","https://openalex.org/W2923014074","https://openalex.org/W2946609015","https://openalex.org/W2949858875","https://openalex.org/W2951286828","https://openalex.org/W2952984539","https://openalex.org/W2963341956","https://openalex.org/W2963383094","https://openalex.org/W2963748441","https://openalex.org/W2983984338","https://openalex.org/W2990138404","https://openalex.org/W3035267217","https://openalex.org/W3035507081","https://openalex.org/W3103649165","https://openalex.org/W3171654528","https://openalex.org/W3172399575","https://openalex.org/W3175487198","https://openalex.org/W3193717459","https://openalex.org/W4223598532","https://openalex.org/W4285302136","https://openalex.org/W4288287305","https://openalex.org/W6691459498","https://openalex.org/W6757817989","https://openalex.org/W6762392948","https://openalex.org/W6771271773","https://openalex.org/W6794339910","https://openalex.org/W6796401879","https://openalex.org/W6803845766","https://openalex.org/W6810879928"],"related_works":["https://openalex.org/W3090591275","https://openalex.org/W2735571786","https://openalex.org/W4281704574","https://openalex.org/W3208882810","https://openalex.org/W2972862903","https://openalex.org/W3099765033","https://openalex.org/W4288419306","https://openalex.org/W2921259037","https://openalex.org/W2970699417","https://openalex.org/W2987302549"],"abstract_inverted_index":{"Abstract":[0],"In":[1,85],"behavioral":[2,27,67,96,119],"testing,":[3],"system":[4],"functionalities":[5,135],"underrepresented":[6],"in":[7,41],"the":[8,26,42,56,59,66,79,118,156],"standard":[9],"evaluation":[10],"setting":[11],"(with":[12],"a":[13,159],"held-out":[14],"test":[15,68,120],"set)":[16],"are":[17],"validated":[18],"through":[19],"controlled":[20,122],"input-output":[21],"pairs.":[22],"Optimizing":[23],"performance":[24],"on":[25,114,168],"tests":[28],"during":[29],"training":[30],"(behavioral":[31],"learning)":[32],"would":[33],"improve":[34],"coverage":[35],"of":[36,75,78,82,102,117,158,162],"phenomena":[37],"not":[38],"sufficiently":[39],"represented":[40],"i.i.d.":[43],"data":[44],"and":[45,73,111,151,154,164],"could":[46],"lead":[47],"to":[48,71,123,133,141],"seemingly":[49],"more":[50],"robust":[51],"models.":[52],"However,":[53],"there":[54],"is":[55],"risk":[57],"that":[58],"model":[60,76],"narrowly":[61],"captures":[62],"spurious":[63],"correlations":[64],"from":[65],"suite,":[69],"leading":[70],"overestimation":[72],"misrepresentation":[74],"performance\u2014one":[77],"original":[80],"pitfalls":[81],"traditional":[83],"evaluation.":[84],"this":[86],"work,":[87],"we":[88],"introduce":[89],"BeLUGA,":[90],"an":[91],"analysis":[92],"method":[93],"for":[94],"evaluating":[95],"learning":[97],"considering":[98],"generalization":[99,132,166,169],"across":[100],"dimensions":[101],"different":[103],"granularity":[104],"levels.":[105],"We":[106,138],"optimize":[107],"behavior-specific":[108],"loss":[109],"functions":[110],"evaluate":[112],"models":[113],"several":[115],"partitions":[116],"suite":[121],"leave":[124],"out":[125],"specific":[126],"phenomena.":[127],"An":[128],"aggregate":[129],"score":[130],"measures":[131],"unseen":[134],"(or":[136],"overfitting).":[137],"use":[139],"BeLUGA":[140],"examine":[142],"three":[143],"representative":[144],"NLP":[145],"tasks":[146],"(sentiment":[147],"analysis,":[148],"paraphrase":[149],"identification,":[150],"reading":[152],"comprehension)":[153],"compare":[155],"impact":[157],"diverse":[160],"set":[161],"regularization":[163],"domain":[165],"methods":[167],"performance.1":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2023-08-17T00:00:00"}