{"id":"W2768091364","doi":"10.48550/arxiv.1711.02013","title":"Neural Language Modeling by Jointly Learning Syntax and Lexicon","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Parsing; Natural language processing; Syntax; Language model; Leverage (statistics); Tree structure; Artificial neural network; Lexicon; Recurrent neural network; Data structure; Programming language","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":[0.0002550011,0.0002866448,0.0003136617,0.0001437619,0.0003541329,0.0003798886,0.00153722,0.0002433393,0.0000077591],"category_scores_gemma":[0.0000613076,0.000342044,0.0001139691,0.00007524271,0.00006524704,0.000541691,0.002799284,0.000906209,0.00001658473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009334191,"about_ca_system_score_gemma":0.00009039605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007852003,"about_ca_topic_score_gemma":0.00003625863,"domain_scores_codex":[0.9981277,0.0001113649,0.0001668702,0.00114772,0.00009281802,0.0003535191],"domain_scores_gemma":[0.9983047,0.00004603571,0.0002286071,0.00119487,0.00006401283,0.0001618301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008872195,0.00001919488,0.001321309,0.00007668536,0.00004266149,0.0002783083,0.0008892033,0.9721698,0.0002864542,0.01979023,0.00005087425,0.005066387],"study_design_scores_gemma":[0.0002305025,0.00001932855,0.00002886403,0.00008266731,0.00002595656,0.000008267316,0.000130938,0.9922576,0.00007138787,0.006736883,0.00005899608,0.0003486172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4711422,0.0002428589,0.5269932,0.0001103923,0.0002191938,0.00008952243,0.000002914261,0.0001715252,0.001028195],"genre_scores_gemma":[0.9954835,0.0001420357,0.002155339,0.00005567931,0.00007482949,4.820203e-7,0.000008236185,0.0000188117,0.002061043],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5248379,"threshold_uncertainty_score":0.9999031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07486587234654331,"score_gpt":0.1969179462444041,"score_spread":0.1220520738978608,"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."}}