{"id":"W2806901754","doi":"10.18653/v1/s18-2016","title":"Coarse Lexical Frame Acquisition at the Syntax–Semantics Interface Using a Latent-Variable PCFG Model","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Computer science; Natural language processing; Artificial intelligence; Rule-based machine translation; Bayesian network; Frame (networking); Merge (version control); Latent variable; Syntax; Semantics (computer science); Programming language; Information retrieval","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":[0.001467046,0.0009583667,0.0009265375,0.001695124,0.0007627596,0.001792558,0.002071215,0.001351721,0.00606952],"category_scores_gemma":[0.005399259,0.0008031428,0.001194467,0.001236212,0.001236375,0.003764224,0.001756664,0.00241593,0.001794367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001196395,"about_ca_system_score_gemma":0.002105184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01096884,"about_ca_topic_score_gemma":0.01841405,"domain_scores_codex":[0.9987669,0.0004042879,0.00004904374,0.0004692821,0.0002137045,0.00009681699],"domain_scores_gemma":[0.9977816,0.001287832,0.0001169969,0.0004011969,0.0003367591,0.00007563904],"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":[0.0003967799,0.0003202555,0.004924243,0.0003403008,0.0001548374,0.0006323049,0.001961651,0.2031876,0.04808223,0.1236709,0.01314959,0.6031794],"study_design_scores_gemma":[0.00002355301,0.0000310519,0.0007799247,0.00001899218,0.00002577885,0.00007521683,0.00008375318,0.9342471,0.008202226,0.05294152,0.003540662,0.0000302262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01526763,0.00005773114,0.980335,0.0001221855,0.00001358848,0.00007211309,0.0002582092,0.002706613,0.001166939],"genre_scores_gemma":[0.3021684,0.00009189918,0.6921954,0.0001538215,0.00003243487,0.0002562196,0.001372558,0.001061891,0.002667307],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01096884,"threshold_uncertainty_score":0.02181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0272718793033293,"score_gpt":0.3050964610847725,"score_spread":0.2778245817814431,"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."}}