{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006941034,0.0009872579,0.0007446148,0.001154619,0.0002835988,0.001100456,0.001831679,0.0009219698,0.001762929],"category_scores_gemma":[0.002739105,0.0006565458,0.001218029,0.00106577,0.0004969382,0.003598846,0.0009547394,0.001705952,0.001229036],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007345015,"about_ca_system_score_gemma":0.001109387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00467921,"about_ca_topic_score_gemma":0.008670865,"domain_scores_codex":[0.9995949,0.000138096,0.0000215086,0.0001496727,0.00006020413,0.00003565008],"domain_scores_gemma":[0.9993644,0.0003376155,0.00008573946,0.00007892228,0.0001071976,0.00002608281],"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":[0.0001451285,0.0001367753,0.001812091,0.0001806884,0.0002213459,0.0002610724,0.0002079616,0.6520839,0.01042677,0.04827154,0.007439089,0.2788136],"study_design_scores_gemma":[0.000005623112,0.00001034711,0.00007019924,0.000003747047,0.00001313261,0.00001675929,0.000005418183,0.9790096,0.0006439032,0.01967258,0.0005422456,0.000006413851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02106926,0.0003331912,0.974076,0.0004181885,0.00005746154,0.00004022337,0.0003516631,0.001864697,0.001789306],"genre_scores_gemma":[0.6539182,0.000939884,0.3305119,0.000449968,0.0002037896,0.0004071656,0.00312851,0.0006393463,0.00980124],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00467921,"threshold_uncertainty_score":0.009303927,"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."}}