{"id":"W2080021477","doi":"10.1016/j.neucom.2008.12.025","title":"Improving a statistical language model through non-linear prediction","year":2009,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Perplexity; Computer science; Feature (linguistics); Context (archaeology); Artificial intelligence; Language model; Word (group theory); Feature vector; Linear model; Term (time); Pattern recognition (psychology); Machine learning; Mathematics","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":[0.0001882533,0.0001686382,0.0001572467,0.00006844739,0.0001819166,0.0001658192,0.000660188,0.00007437052,0.000001277107],"category_scores_gemma":[0.0001145524,0.000157384,0.00004193915,0.0002864966,0.00002086855,0.000594704,0.0002256514,0.0003672092,0.000008191821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003815587,"about_ca_system_score_gemma":0.00005321897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002123522,"about_ca_topic_score_gemma":4.303384e-7,"domain_scores_codex":[0.9985556,0.00003611482,0.0002610665,0.0004972139,0.0002877287,0.0003622785],"domain_scores_gemma":[0.9993036,0.00007155387,0.0001136283,0.000384105,0.00006108204,0.00006601197],"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":[0.00001452403,0.000143205,0.00006220087,0.00007358563,0.000006906423,0.0002450266,0.004258526,0.008012951,0.1371715,0.05838082,0.001079021,0.7905518],"study_design_scores_gemma":[0.0001529301,0.0000999729,0.00008800903,0.00003068558,0.000004048886,0.00004355107,0.000009016005,0.9756703,0.01243697,0.01129982,0.00002173969,0.0001429651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01098727,0.0001303061,0.986347,0.0002880303,0.0001120879,0.0001621206,0.000003361271,0.001426808,0.0005429999],"genre_scores_gemma":[0.4693782,7.80414e-7,0.529645,0.0008438464,0.0001024665,0.000001725852,0.000002604525,0.000007460282,0.00001796237],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9676573,"threshold_uncertainty_score":0.6417933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01265086074894661,"score_gpt":0.2861839819035844,"score_spread":0.2735331211546377,"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."}}