{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000559666,0.0001517591,0.0001533544,0.000112633,0.0009546533,0.0001503843,0.0007766532,0.00004375633,0.0003491073],"category_scores_gemma":[0.00002577447,0.0001334715,0.00005675885,0.0006722228,0.00006606142,0.0005952587,0.0003939467,0.0002032116,0.00005071624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004715718,"about_ca_system_score_gemma":0.0001225144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001881948,"about_ca_topic_score_gemma":0.00009266152,"domain_scores_codex":[0.9979826,0.0001752073,0.0002764903,0.0006574003,0.0006096776,0.0002986281],"domain_scores_gemma":[0.9987297,0.00006434123,0.0001232938,0.0009063903,0.00007784311,0.00009842546],"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":[0.0003550065,0.0006444748,0.01272149,0.00006058362,0.00008426898,0.00004429988,0.004285879,0.03447599,0.1219405,0.7796037,0.002942526,0.04284133],"study_design_scores_gemma":[0.002203307,0.0005707814,0.1204805,0.00001753009,0.00005270213,0.0003277819,0.0002994514,0.7025131,0.02074926,0.0131454,0.1383726,0.001267535],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3697605,0.00005651517,0.6265242,0.002068682,0.0001527478,0.0003561738,0.00002048249,0.0003164841,0.0007441752],"genre_scores_gemma":[0.9941519,0.000004255117,0.004442242,0.0003383794,0.0000314705,0.0001589145,0.0002066626,0.000009658635,0.000656475],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7664583,"threshold_uncertainty_score":0.7342517,"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."}}