{"id":"W3036182276","doi":"10.48550/arxiv.2006.09639","title":"Iterative Edit-Based Unsupervised Sentence Simplification","year":2020,"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":"University of Waterloo","funders":"","keywords":"Sentence; Computer science; Phrase; Simplicity; Artificial intelligence; Fluency; Natural language processing; Set (abstract data type); Word (group theory); Function (biology); Machine learning; 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":[0.0002302774,0.0003446403,0.0003289488,0.000178172,0.000204406,0.0002435362,0.002164864,0.0003011434,0.00002877496],"category_scores_gemma":[0.0001064534,0.000401045,0.0002216088,0.0008161443,0.0001402313,0.0005234692,0.0008242921,0.0006045314,0.0002030435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002696282,"about_ca_system_score_gemma":0.0004256358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000929113,"about_ca_topic_score_gemma":0.00001965316,"domain_scores_codex":[0.9973773,0.0002710268,0.000286629,0.001603889,0.0001550729,0.0003061305],"domain_scores_gemma":[0.9972086,0.0002023456,0.0002906782,0.001718372,0.000339355,0.0002406654],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001422214,0.0005667506,0.005168611,0.0004628384,0.0001625008,0.0002209307,0.00241752,0.293644,0.002882369,0.6859924,0.002032662,0.006307122],"study_design_scores_gemma":[0.0003589065,0.00005797147,0.004754592,0.00005542193,0.00004172814,0.000001202978,0.00008219216,0.9463455,0.001134275,0.04555733,0.001144339,0.0004665274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06136396,0.00002329179,0.9340169,0.002431111,0.000483842,0.0004862108,0.00004185705,0.000487336,0.000665429],"genre_scores_gemma":[0.9949284,0.00002264823,0.004116056,0.0005038104,0.0001231156,0.000004142664,0.000128638,0.00001510038,0.0001580996],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9335644,"threshold_uncertainty_score":0.9998441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1068087120810845,"score_gpt":0.2009478128661213,"score_spread":0.09413910078503683,"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."}}