{"id":"W2891563639","doi":"10.3758/s13428-018-1118-4","title":"Conceptualizing syntactic categories as semantic categories: Unifying part-of-speech identification and semantics using co-occurrence vector averaging","year":2018,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Simple (philosophy); Word (group theory); Replicate; Semantics (computer science); Identification (biology); Class (philosophy); Linguistics; Mathematics; Programming language; Statistics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002985502,0.0008135096,0.0008982251,0.004089392,0.0004650927,0.002150452,0.001423374,0.001025616,0.001402452],"category_scores_gemma":[0.009558542,0.0004205038,0.0009650945,0.003020817,0.001834141,0.006611129,0.001745311,0.001470068,0.0007108536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006923252,"about_ca_system_score_gemma":0.0007741193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003002981,"about_ca_topic_score_gemma":0.003132962,"domain_scores_codex":[0.9988756,0.0004464157,0.00006190647,0.0003344019,0.0001986393,0.00008302952],"domain_scores_gemma":[0.9962857,0.00210224,0.000387174,0.0007947524,0.0002975817,0.0001325126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003853088,0.0003061462,0.01979681,0.0002706995,0.0004662281,0.0002561851,0.00207612,0.06185067,0.02637217,0.1585502,0.00267887,0.7269905],"study_design_scores_gemma":[0.00001176242,0.00009384641,0.009386844,0.00004934608,0.00007575066,0.0001779405,0.0003311393,0.632684,0.003491248,0.3512032,0.002416332,0.00007847729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05234019,0.0006442369,0.9441289,0.0003050395,0.00006235705,0.00004807522,0.0001549409,0.0004656157,0.00185052],"genre_scores_gemma":[0.7642238,0.0005874538,0.2331649,0.0001194534,0.00009165586,0.0001133377,0.0004165049,0.0001780911,0.001104816],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004089392,"threshold_uncertainty_score":0.01578903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3004789857609664,"score_gpt":0.5616148356223938,"score_spread":0.2611358498614274,"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."}}