{"id":"W2943085977","doi":"","title":"Brief Report: Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Parsing; Artificial intelligence; Language model; Syntax; Tree structure; Tree (set theory); Recurrent neural network; Natural language processing; Artificial neural network; Machine learning; Algorithm; Binary tree; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001658449,0.0009426411,0.0005741089,0.0004161593,0.0003089254,0.001765604,0.002048209,0.001647666,0.01225963],"category_scores_gemma":[0.005938718,0.0005749714,0.0008095545,0.0008345314,0.0005057819,0.003092707,0.001155178,0.00281245,0.006599424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007137909,"about_ca_system_score_gemma":0.0008009113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004773901,"about_ca_topic_score_gemma":0.004541619,"domain_scores_codex":[0.9995095,0.0001596179,0.00003352448,0.0001363693,0.000123401,0.00003760713],"domain_scores_gemma":[0.9985386,0.0005917597,0.00007602944,0.0001633713,0.0004771963,0.0001529595],"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":[0.0003704507,0.0001947661,0.002849763,0.0007383519,0.0003873582,0.0004394758,0.0003129715,0.1632198,0.009265589,0.06760303,0.1788181,0.5758004],"study_design_scores_gemma":[0.00008673592,0.0001824525,0.0007715387,0.0001252972,0.0001488427,0.0001831598,0.00004161222,0.8435679,0.005999983,0.08034243,0.06845532,0.00009473332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01050912,0.00828914,0.9541781,0.006498829,0.00425592,0.0001826832,0.001187198,0.005619485,0.00927952],"genre_scores_gemma":[0.2192254,0.01664152,0.6895276,0.002340162,0.00784137,0.0006383728,0.00662401,0.002790089,0.05437151],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01225963,"threshold_uncertainty_score":0.04101259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0245396822179179,"score_gpt":0.3385625186261699,"score_spread":0.314022836408252,"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."}}