{"id":"W4309376528","doi":"10.2196/38095","title":"Medical Text Simplification Using Reinforcement Learning (TESLEA): Deep Learning–Based Text Simplification Approach","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"NOSM University; Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Lakehead University","keywords":"Computer science; Reinforcement learning; Readability; Annotation; Jargon; Fluency; Artificial intelligence; Natural language processing; Text simplification; Quality (philosophy); Relevance (law); Information retrieval; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.003457372,0.0003619314,0.0004261716,0.0003766144,0.001358779,0.0002845875,0.002230915,0.0003636944,0.0009085513],"category_scores_gemma":[0.001173788,0.0003547733,0.0001808739,0.001409143,0.000255843,0.0009593893,0.0008346532,0.001994221,0.0001428281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005865489,"about_ca_system_score_gemma":0.0008554881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003446995,"about_ca_topic_score_gemma":0.000002149922,"domain_scores_codex":[0.9924575,0.0005305547,0.00170807,0.0004938526,0.004085995,0.0007240352],"domain_scores_gemma":[0.9966801,0.0005236838,0.0008560448,0.001053959,0.0002391603,0.0006470571],"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":[0.00008345672,0.001216411,0.001758612,0.0006418399,0.0000875066,0.00001290992,0.02394315,0.4246352,0.000240176,0.0535692,0.001342767,0.4924688],"study_design_scores_gemma":[0.00071151,0.0002019188,0.0006082261,0.00002900346,0.0000146863,0.00007339813,0.002695997,0.9421018,0.00007286251,0.0002244808,0.05287806,0.0003880484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02889597,0.00006400915,0.9653757,0.001404428,0.000235998,0.0008291014,0.000001873867,0.0005983739,0.002594505],"genre_scores_gemma":[0.9815225,0.00001829529,0.01537146,0.001950613,0.0001313895,0.000428726,0.0003674202,0.00003067453,0.0001789275],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9526265,"threshold_uncertainty_score":0.9999413,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02522489423537592,"score_gpt":0.2855421848158192,"score_spread":0.2603172905804432,"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."}}