{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006135354,0.0002436524,0.0004072242,0.0004028352,0.0007857362,0.0002221473,0.0003412473,0.0001587796,0.0006569247],"category_scores_gemma":[0.001290833,0.000244268,0.00006342596,0.0007843095,0.001143398,0.0002222359,0.0002129355,0.0006978997,0.00008939923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001364019,"about_ca_system_score_gemma":0.0002723835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007404246,"about_ca_topic_score_gemma":0.00001502402,"domain_scores_codex":[0.9951642,0.002111788,0.0006258973,0.0007334347,0.0006228691,0.0007418068],"domain_scores_gemma":[0.9972318,0.001136732,0.0002632208,0.0005421985,0.0006304604,0.0001956017],"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":[0.0003173976,0.0005405298,0.2548915,0.0006275299,0.0002844515,0.0003133266,0.1080583,0.000004696854,0.3831398,0.03077224,0.0006564519,0.2203937],"study_design_scores_gemma":[0.002420963,0.001530992,0.3734679,0.001333505,0.0005696007,0.0009911808,0.09264276,0.001661153,0.4711146,0.002827674,0.04911518,0.002324486],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873888,0.00059913,0.009566789,0.0001243366,0.0009457604,0.0005682438,0.0000223159,0.00008381104,0.0007007653],"genre_scores_gemma":[0.984125,0.00006513262,0.01488401,0.00001569349,0.0002588188,0.00005668917,0.00003435605,0.00003962017,0.0005206536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2180693,"threshold_uncertainty_score":0.9960959,"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."}}