{"id":"W2944617758","doi":"10.1111/cogs.12730","title":"The Role of Negative Information in Distributional Semantic Learning","year":2019,"lang":"en","type":"article","venue":"Cognitive Science","topic":"Topic Modeling","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Word2vec; Computer science; Word embedding; Artificial intelligence; Context (archaeology); Natural language processing; Word (group theory); Representation (politics); Semantics (computer science); Machine learning; Embedding; Mathematics","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":[0.008051501,0.001595538,0.001518978,0.001880542,0.00120782,0.003663609,0.002555666,0.001970365,0.003405303],"category_scores_gemma":[0.05191263,0.0008956694,0.0009233917,0.00148607,0.005814232,0.01461516,0.004730666,0.004313815,0.000676193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001389645,"about_ca_system_score_gemma":0.0009023279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001957294,"about_ca_topic_score_gemma":0.001806439,"domain_scores_codex":[0.9948783,0.002159019,0.0002887155,0.001407314,0.001100385,0.0001663227],"domain_scores_gemma":[0.9708076,0.02159902,0.001436756,0.003101727,0.002330051,0.0007247654],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00109297,0.0003563083,0.02341478,0.0006188631,0.0002711443,0.000538003,0.001755505,0.06187776,0.007078017,0.55288,0.009073834,0.3410428],"study_design_scores_gemma":[0.00003417747,0.00009910367,0.001792847,0.00007091062,0.00003577859,0.0002606871,0.0001023922,0.1643281,0.001865154,0.8282825,0.003076851,0.00005160097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1096402,0.002606126,0.8663344,0.005074501,0.0003829831,0.00009025839,0.0005121192,0.0008423339,0.01451699],"genre_scores_gemma":[0.9306716,0.001143092,0.06112294,0.001352901,0.0005019492,0.0001191473,0.0009097678,0.0002996513,0.003879116],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008051501,"threshold_uncertainty_score":0.0425809,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007649209568656575,"score_gpt":0.2372489986065929,"score_spread":0.2295997890379363,"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."}}