{"id":"W4287855019","doi":"10.18653/v1/2022.semeval-1.16","title":"UAlberta at SemEval 2022 Task 2: Leveraging Glosses and Translations for Multilingual Idiomaticity Detection","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Machine Intelligence Institute","keywords":"Computer science; SemEval; Literal (mathematical logic); Natural language processing; Artificial intelligence; Task (project management); Classifier (UML); Literal translation; Leverage (statistics); Linguistics; Source text; Programming language","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.005690192,0.0026315,0.00202083,0.005648793,0.003078207,0.006579258,0.00247639,0.002105541,0.03776245],"category_scores_gemma":[0.01455788,0.001063801,0.00110781,0.003086934,0.001100794,0.00820922,0.006125794,0.002547967,0.02769787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003411023,"about_ca_system_score_gemma":0.0041471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08987679,"about_ca_topic_score_gemma":0.1190117,"domain_scores_codex":[0.9940204,0.001813543,0.0003619234,0.001454803,0.001879063,0.0004702444],"domain_scores_gemma":[0.9927538,0.001810945,0.0003118672,0.001860459,0.002758199,0.0005047324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001581715,0.0005863218,0.00527743,0.002066827,0.0003093613,0.0007324034,0.001582444,0.002283108,0.02828838,0.01769393,0.4455341,0.4940639],"study_design_scores_gemma":[0.00083358,0.0004547596,0.02462822,0.001119715,0.0003795544,0.001688355,0.003519713,0.1175764,0.05719564,0.03474144,0.7574422,0.0004203132],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1304367,0.01086531,0.2875671,0.005588945,0.002488454,0.00281734,0.1386888,0.2170633,0.2044842],"genre_scores_gemma":[0.2889541,0.002020278,0.3560401,0.001600773,0.0002893249,0.00148273,0.2766535,0.01384273,0.05911645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08987679,"threshold_uncertainty_score":0.1787072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03128321214141992,"score_gpt":0.3218947493615454,"score_spread":0.2906115372201254,"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."}}