{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001419973,0.00006059893,0.00004787343,0.00004536256,0.00007055716,0.00007942611,0.0003276737,0.00003074582,0.000006213646],"category_scores_gemma":[0.0000060439,0.00004612031,0.000009443542,0.0001642929,0.00002622049,0.001014689,0.00005892635,0.00005639818,0.00001354721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001837225,"about_ca_system_score_gemma":0.00001989681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002825695,"about_ca_topic_score_gemma":0.0001241093,"domain_scores_codex":[0.9992522,0.00002603361,0.00008857573,0.0003650927,0.0001421242,0.000125947],"domain_scores_gemma":[0.9989733,0.000005132292,0.00003342994,0.0008664824,0.00007042669,0.00005121069],"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":[0.00001463669,0.00006366041,0.0002226399,0.000004557024,0.000007644019,0.000004597021,0.006018043,0.00324621,0.006262382,0.2909712,0.0001556819,0.6930288],"study_design_scores_gemma":[0.0000961628,0.0001407747,0.0003009505,0.00000197944,0.000001503793,0.00002199473,0.0001301647,0.9921283,0.003860719,0.003150087,0.00008754215,0.00007984134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3762518,0.000004497692,0.6208243,0.0003069935,0.00006689994,0.00005021716,9.216451e-8,0.0001955179,0.002299768],"genre_scores_gemma":[0.886084,3.889676e-7,0.113167,0.0002515406,0.0001823081,0.0000057498,0.00000210869,0.000004588017,0.0003023277],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9888821,"threshold_uncertainty_score":0.1880732,"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."}}