{"id":"W3060766412","doi":"10.48550/arxiv.2008.08612","title":"A Survey on Text Simplification","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Field (mathematics); Natural language processing; Focus (optics); Artificial intelligence; Text simplification; Similarity (geometry); Semantic similarity; Information retrieval; Data science; Sentence","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":[0.0004134908,0.0002743859,0.0002822397,0.0001571934,0.0001452664,0.0001710831,0.002096962,0.0002902298,0.00002047042],"category_scores_gemma":[0.0001898632,0.0003195747,0.0001551216,0.000726861,0.00007709496,0.000249025,0.000955223,0.0005812609,0.0006004074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002303033,"about_ca_system_score_gemma":0.0002198255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003809143,"about_ca_topic_score_gemma":0.0001214431,"domain_scores_codex":[0.9975938,0.0003651245,0.0002234497,0.001446241,0.0001190978,0.0002522641],"domain_scores_gemma":[0.9971834,0.0003066442,0.0002534097,0.001876777,0.0001844173,0.0001953327],"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":[0.000117294,0.0004106465,0.01126018,0.0001222556,0.0001141026,0.0000760185,0.0007039997,0.09007581,0.0001970677,0.8798503,0.004230445,0.01284192],"study_design_scores_gemma":[0.000320514,0.000118079,0.3293927,0.00004468177,0.0000323919,0.000001020477,0.00002582117,0.5701264,0.0002550592,0.09703887,0.001983116,0.0006613653],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1379866,0.00001913066,0.8575143,0.001035502,0.000390079,0.0004218821,0.00006969341,0.0004629722,0.002099846],"genre_scores_gemma":[0.9985988,0.00003985692,0.0004531105,0.0002797252,0.00005330804,0.000001395117,0.0001429422,0.00001395625,0.000416871],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8606122,"threshold_uncertainty_score":0.9999256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1624201718261306,"score_gpt":0.212521016995471,"score_spread":0.05010084516934041,"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."}}