{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00160365,0.000527351,0.000460519,0.001237923,0.0005480558,0.0002332103,0.0002512079,0.0003245406,0.0002534833],"category_scores_gemma":[0.0006854745,0.0005318206,0.00009741586,0.001353342,0.001090554,0.0004897477,0.0001124114,0.0001949835,0.001143748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006858231,"about_ca_system_score_gemma":0.0003971806,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001287296,"about_ca_topic_score_gemma":0.05724712,"domain_scores_codex":[0.9960683,0.0001121509,0.0005619751,0.001335823,0.00121081,0.0007109225],"domain_scores_gemma":[0.997902,0.0006417365,0.0005859097,0.0003807659,0.0002488773,0.0002407262],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008130299,0.0004324024,0.0006286952,0.0004518795,0.0002546159,0.00001944619,0.007027996,0.0006830389,0.1402108,0.0008255958,0.09342121,0.7552313],"study_design_scores_gemma":[0.01176554,0.0008101253,0.001665249,0.001197879,0.0007393233,0.0000431937,0.004244287,0.8014023,0.008849296,0.0007771992,0.1655511,0.002954482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6980157,0.006384244,0.08865432,0.006043427,0.02371303,0.0516376,0.02011766,0.01958709,0.08584688],"genre_scores_gemma":[0.564046,0.0001975499,0.01004168,0.0003101215,0.001515475,0.0004392592,0.004089206,0.003806407,0.4155543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8007193,"threshold_uncertainty_score":0.9997134,"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."}}