{"id":"W4377220848","doi":"10.5334/joc.278","title":"A New Corpus of Lexical Substitution and Word Blend Errors: Probing the Semantic Structure of Lemma Access Failures","year":2023,"lang":"en","type":"article","venue":"Journal of Cognition","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University","keywords":"Lemma (botany); Substitution (logic); Computer science; Natural language processing; Sentence; Artificial intelligence; Word (group theory); Set (abstract data type); Part of speech; Speech production; Selection (genetic algorithm); Linguistics; Speech recognition","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002550065,0.00007144159,0.0001553413,0.0001949873,0.00005370458,0.00009270698,0.0003939105,0.00005541552,0.000004517903],"category_scores_gemma":[0.0001463403,0.000045173,0.00004561012,0.000493825,0.0000647292,0.0007770885,0.0001078425,0.0002027675,2.455745e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001244261,"about_ca_system_score_gemma":0.0001102692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001651834,"about_ca_topic_score_gemma":0.00001483194,"domain_scores_codex":[0.9991604,0.00005276902,0.0003057914,0.00008643258,0.0003007608,0.00009384351],"domain_scores_gemma":[0.9990133,0.00009460233,0.0005004777,0.00009588481,0.0002605571,0.00003519984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002044735,0.00006470985,0.001220572,0.0006899498,0.0001307563,0.00009057589,0.003439788,0.0001596119,0.6681648,0.03198105,0.001678712,0.292175],"study_design_scores_gemma":[0.000704161,0.0002492134,0.007526436,0.001425189,0.00009948703,0.0004931578,0.0001030459,0.00287618,0.6413144,0.344951,0.0001002858,0.0001574112],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7211151,0.001189119,0.2756268,0.001680321,0.0001721924,0.0001405217,0.00000303469,0.00005650266,0.00001641235],"genre_scores_gemma":[0.9708457,0.00004011625,0.02899118,0.00003108737,0.00007928819,4.41319e-7,0.000001391539,0.000003716274,0.000007059642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.31297,"threshold_uncertainty_score":0.1842102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02451911689282927,"score_gpt":0.299843421022039,"score_spread":0.2753243041292097,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}