{"id":"W4233906699","doi":"10.1007/10985687_6","title":"Neural Probabilistic Language Models","year":2006,"lang":"en","type":"book-chapter","venue":"Studies in fuzziness and soft computing","topic":"Topic Modeling","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Generalization; Sentence; Curse of dimensionality; Artificial intelligence; Language model; Word (group theory); Natural language processing; Probabilistic logic; Representation (politics); Sequence (biology); Set (abstract data type); Linguistics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002950556,0.0003633644,0.0006040433,0.0001543724,0.000176529,0.00009316354,0.0004877559,0.0001320482,9.323401e-7],"category_scores_gemma":[0.00004743365,0.0003310565,0.00007280253,0.00006237663,0.0001485864,0.00015221,0.001270565,0.0003709879,0.000002243497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007939311,"about_ca_system_score_gemma":0.00003220838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004746499,"about_ca_topic_score_gemma":0.00004469335,"domain_scores_codex":[0.9981539,0.00002309636,0.0004936417,0.0007218032,0.0002547233,0.0003528635],"domain_scores_gemma":[0.9989418,0.0002672193,0.0001778829,0.0004562956,0.0001140529,0.000042707],"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":[0.000004525726,0.0000250954,0.0001388759,0.0008897122,0.00009281626,0.0003703304,0.007625362,0.1589972,0.000002256545,0.6491045,0.0006023392,0.182147],"study_design_scores_gemma":[0.0002364083,0.00001948102,0.00003816926,0.000516669,0.00001423674,0.0000232862,0.0001085074,0.9026673,3.478888e-7,0.09559634,0.000359661,0.0004195994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009684354,0.0469612,0.6373674,0.0006461299,0.003195519,0.001045711,0.00001164707,0.0007507483,0.3003373],"genre_scores_gemma":[0.9551972,0.0002281498,0.01779935,0.0002504923,0.0008340024,0.00001316003,0.000008293663,0.0000651977,0.02560421],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9455128,"threshold_uncertainty_score":0.9999142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0560900774048932,"score_gpt":0.287402023592984,"score_spread":0.2313119461880908,"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."}}