{"id":"W6891689306","doi":"10.48448/wr6s-b387","title":"UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguation","year":2023,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Task (project management); Context (archaeology); Word (group theory); Machine translation; Rank (graph theory); Encoder; Word-sense disambiguation","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005198088,0.004446866,0.002261273,0.003742723,0.003372504,0.007112665,0.00367512,0.003127914,0.09680779],"category_scores_gemma":[0.008682854,0.001111672,0.001578629,0.002683564,0.001528102,0.004694603,0.006847629,0.00321046,0.1142043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003100303,"about_ca_system_score_gemma":0.005295238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08569996,"about_ca_topic_score_gemma":0.1065852,"domain_scores_codex":[0.9952484,0.0009825024,0.000209599,0.001593112,0.001428201,0.0005381739],"domain_scores_gemma":[0.9936579,0.000740675,0.0001616151,0.001885578,0.002503986,0.00105033],"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":[0.0005852864,0.0002394865,0.000767164,0.0005665459,0.00008035758,0.0002681846,0.0002369977,0.001240813,0.005724667,0.003596648,0.7579802,0.2287137],"study_design_scores_gemma":[0.0003054646,0.0001700754,0.002986906,0.0003699056,0.00006012942,0.000388431,0.0007287149,0.02127348,0.01691887,0.01306755,0.9435874,0.0001431367],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.03548612,0.01309993,0.1664699,0.01054906,0.01573838,0.001509951,0.1507653,0.3384945,0.2678868],"genre_scores_gemma":[0.09615824,0.002690502,0.2406418,0.002624481,0.001139375,0.0009754174,0.3791928,0.03304173,0.2435357],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.09680779,"threshold_uncertainty_score":0.3238543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05143506260081366,"score_gpt":0.3679547414787159,"score_spread":0.3165196788779022,"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."}}