{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001442117,0.0004171608,0.0005722714,0.003268139,0.001091591,0.001180242,0.0008362728,0.0008297402,0.003493189],"category_scores_gemma":[0.01373193,0.0002965449,0.0002807469,0.003243679,0.001858749,0.001694045,0.002393258,0.001174554,0.001386111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003702475,"about_ca_system_score_gemma":0.0007049771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003089579,"about_ca_topic_score_gemma":0.00732089,"domain_scores_codex":[0.9981431,0.0005116043,0.0003197916,0.0004722883,0.0004745182,0.00007861322],"domain_scores_gemma":[0.9646106,0.02218076,0.002736793,0.006128233,0.003353965,0.000989709],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002400432,0.002621799,0.2343095,0.005445632,0.0005119301,0.009893249,0.07704973,0.003103147,0.1478478,0.009872966,0.05635292,0.4505908],"study_design_scores_gemma":[0.0002523569,0.000603214,0.7812124,0.0003958608,0.0002967138,0.01388824,0.01625239,0.007555193,0.03841173,0.005585597,0.1352877,0.000258617],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9673939,0.0009069982,0.007651214,0.0003053694,0.00009272333,0.0002029033,0.01754783,0.0003083835,0.005590714],"genre_scores_gemma":[0.9271365,0.000831046,0.01850299,0.0002030418,0.0001210499,0.0006792633,0.04812324,0.0002981489,0.004104735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003493189,"threshold_uncertainty_score":0.01168591,"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."}}