{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006023303,0.0008808132,0.0005787142,0.002029439,0.0002339314,0.0006202618,0.0007200313,0.0007987837,0.00170397],"category_scores_gemma":[0.003905407,0.00025351,0.0006538464,0.001798105,0.0004226567,0.001819539,0.0007949254,0.001010458,0.0008784583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005614437,"about_ca_system_score_gemma":0.000512371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003740385,"about_ca_topic_score_gemma":0.005566466,"domain_scores_codex":[0.9993907,0.0002483712,0.00003156217,0.0001785038,0.0001016542,0.00004917622],"domain_scores_gemma":[0.998069,0.0010051,0.0002630956,0.0002993411,0.0003086975,0.00005482282],"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":[0.0005120495,0.0004989023,0.0164064,0.0003437295,0.0003061728,0.0003315705,0.0002971281,0.1933344,0.02409407,0.01483159,0.01138835,0.7376556],"study_design_scores_gemma":[0.00001114193,0.0000646844,0.002780767,0.00001303897,0.00002926114,0.00005554934,0.00003936852,0.9755976,0.003983082,0.01642079,0.0009859623,0.0000187551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1745696,0.00069071,0.817441,0.0003081517,0.00005787133,0.00006974167,0.00143008,0.003451546,0.00198128],"genre_scores_gemma":[0.8567464,0.0002833791,0.1356193,0.0000987674,0.00004280021,0.0001322914,0.004100612,0.0002196247,0.002756817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003740385,"threshold_uncertainty_score":0.00743717,"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."}}