{"id":"W3179000338","doi":"10.48550/arxiv.2107.04268","title":"Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Readability; Computer science; Complement (music); Artificial intelligence; Natural language processing; Embedding; Graph; Correlation; Task (project management); Artificial neural network; Deep learning; Machine learning; Theoretical computer science; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007176981,0.0002976209,0.0003797367,0.000195297,0.0003769514,0.0003317308,0.0007802143,0.0002657957,0.00001646441],"category_scores_gemma":[0.0001847996,0.0003206828,0.0002109355,0.0005879831,0.00008993462,0.0007174577,0.0005356339,0.0006924971,0.00000531951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005819801,"about_ca_system_score_gemma":0.0005266994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001020546,"about_ca_topic_score_gemma":0.0001144212,"domain_scores_codex":[0.9975263,0.0003801502,0.0002911305,0.001328946,0.0001541268,0.0003193285],"domain_scores_gemma":[0.9970599,0.0006734577,0.0004483943,0.001292876,0.0003930646,0.0001322372],"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":[0.00003946485,0.0002660565,0.03497726,0.0005927655,0.0001689665,0.0000659244,0.001160244,0.9082915,0.00009007484,0.0487086,0.0000129726,0.005626162],"study_design_scores_gemma":[0.0002512799,0.0001307305,0.02303916,0.0001766348,0.0001321728,0.00001043374,0.0005486824,0.9630063,0.00008077041,0.01221428,0.00003639567,0.0003731432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4484999,0.00000845838,0.5505003,0.000072324,0.0001579899,0.0004112815,0.000003087343,0.0002306414,0.0001159075],"genre_scores_gemma":[0.9599889,0.00001740617,0.03962003,0.00002040522,0.00002289605,0.00001042673,0.00007037625,0.00001739318,0.0002321737],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.511489,"threshold_uncertainty_score":0.9999245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05059178798866121,"score_gpt":0.2244775929815383,"score_spread":0.1738858049928771,"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."}}