{"id":"W2889260178","doi":"10.18653/v1/d18-1544","title":"Grammar Induction with Neural Language Models: An Unusual Replication","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Tencent; Samsung; Nvidia","keywords":"Computer science; Artificial intelligence; Parsing; Grammar; Machine learning; Tree (set theory); Natural language processing; Parse tree; Artificial neural network; Grammar induction; Language model; Tree structure; Rule-based machine translation; Data structure; Linguistics; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01152893,0.0007775094,0.001078972,0.001158152,0.001212461,0.003432209,0.004044252,0.001622487,0.005393598],"category_scores_gemma":[0.05986805,0.0006165713,0.001116392,0.001821045,0.002698344,0.009291713,0.004282318,0.004495285,0.004858084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001506923,"about_ca_system_score_gemma":0.001603366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005173421,"about_ca_topic_score_gemma":0.004322159,"domain_scores_codex":[0.9885317,0.004527444,0.0005611377,0.003762195,0.002318229,0.0002993103],"domain_scores_gemma":[0.9600786,0.0140785,0.0006565934,0.02117047,0.003529014,0.0004868729],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007907328,0.0005343579,0.0248747,0.0008983818,0.0005223953,0.0009297568,0.002592728,0.0573395,0.01476636,0.2077745,0.05582144,0.6331552],"study_design_scores_gemma":[0.0001479471,0.0001972257,0.00538893,0.0002024186,0.0001256833,0.001146465,0.0006920642,0.5094606,0.01406913,0.3929765,0.07545567,0.0001373949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1488751,0.003339795,0.7775342,0.01320007,0.001066985,0.0003082065,0.003813645,0.0094268,0.04243518],"genre_scores_gemma":[0.7629815,0.001144862,0.2149511,0.001917231,0.0004526924,0.0003652659,0.005969192,0.002139948,0.01007833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9884711,"threshold_uncertainty_score":0.0609715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04716170552813,"score_gpt":0.2846948535745075,"score_spread":0.2375331480463775,"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."}}