{"id":"W4386339136","doi":"10.18653/v1/2022.tsar-1.29","title":"RCML at TSAR-2022 Shared Task: Lexical Simplification With Modular Substitution Candidate Ranking","year":2022,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"CBC (Canada)","funders":"","keywords":"Substitution (logic); Computer science; Natural language processing; Task (project management); Ranking (information retrieval); Modular design; Artificial intelligence; Simplicity; Similarity (geometry); Word (group theory); Semantic similarity; Information retrieval; Linguistics; Programming language; Engineering","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":[0.005566561,0.00492642,0.003790847,0.00304383,0.002535526,0.004838671,0.006365501,0.003577198,0.06426805],"category_scores_gemma":[0.02228236,0.001438024,0.002768166,0.002100583,0.00126404,0.006924623,0.008947387,0.004832383,0.05205929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001801811,"about_ca_system_score_gemma":0.004990387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009885743,"about_ca_topic_score_gemma":0.01964572,"domain_scores_codex":[0.9901797,0.003100967,0.0007358891,0.002205946,0.002698829,0.001078708],"domain_scores_gemma":[0.9881123,0.003101804,0.0003888196,0.004377407,0.003261454,0.0007581991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001963979,0.0008671521,0.002094255,0.001537665,0.0004104367,0.001208523,0.000531455,0.01138062,0.03823609,0.00572334,0.5627714,0.3732751],"study_design_scores_gemma":[0.003408668,0.00290011,0.009523791,0.000371048,0.0006179456,0.004016863,0.001857118,0.4597785,0.1141808,0.03753482,0.3649509,0.0008595122],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1613517,0.003738332,0.3450629,0.003635075,0.005701363,0.003289193,0.06361524,0.3361685,0.07743771],"genre_scores_gemma":[0.3918618,0.0005482532,0.2859628,0.001982171,0.001292243,0.002223064,0.2474152,0.02320981,0.04550469],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06426805,"threshold_uncertainty_score":0.2149981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01397615509863767,"score_gpt":0.2235493523136156,"score_spread":0.2095731972149779,"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."}}