{"id":"W2027857109","doi":"10.3115/1620853.1620921","title":"Quadratic features and deep architectures for chunking","year":2009,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Quadratic equation; Generalization; Computer science; Logistic regression; Chunking (psychology); Artificial intelligence; Machine learning; Feature engineering; Quadratic programming; Feature (linguistics); Pattern recognition (psychology); Algorithm; Deep learning; Mathematics; Mathematical optimization","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":[0.00003260313,0.00004788544,0.00004866342,0.00001811036,0.00010608,0.00009767844,0.0001788979,0.00001476014,0.000001392149],"category_scores_gemma":[0.000004679782,0.00003437055,0.00001867842,0.00007521012,0.000009240272,0.00002770744,0.00002259658,0.00003491481,8.422903e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001926954,"about_ca_system_score_gemma":0.000003424666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002090155,"about_ca_topic_score_gemma":0.00001228698,"domain_scores_codex":[0.9996504,0.000004724428,0.00005229889,0.000143769,0.00004181546,0.0001069456],"domain_scores_gemma":[0.9997356,0.00006127281,0.00001506211,0.0001442309,0.000009875444,0.00003397779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001514045,0.00001391027,0.00002827284,0.000002994922,0.000002264741,4.545558e-7,0.0001581407,0.0004556979,0.001108422,0.4521837,0.001834102,0.5442106],"study_design_scores_gemma":[0.0003696619,0.0002280966,0.03635649,0.00001436721,0.00000742557,0.00006664352,0.00001631918,0.2872111,0.005018963,0.662725,0.007674146,0.0003118336],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02521599,0.0003179703,0.9625641,0.009301879,0.00003116488,0.0002012754,2.356768e-7,0.0001154904,0.002251857],"genre_scores_gemma":[0.9035954,0.000003924202,0.09413561,0.001988857,0.00005836019,0.00001161825,3.563714e-7,0.000001465993,0.0002044285],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8783794,"threshold_uncertainty_score":0.140159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009635036367745604,"score_gpt":0.2526397629431815,"score_spread":0.2430047265754359,"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."}}