{"id":"W4385566910","doi":"10.18653/v1/2023.semeval-1.281","title":"UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguation","year":2023,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","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":"SemEval; Computer science; Natural language processing; Task (project management); Encoder; Artificial intelligence; Context (archaeology); Word (group theory); Machine translation; Code (set theory); Word-sense disambiguation; Set (abstract data type); Text segmentation; Test set; Segmentation; Linguistics; Programming language; WordNet","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003807067,0.000138619,0.0001240297,0.0001457247,0.0003097137,0.0001151378,0.0001297104,0.00006619225,0.00001885777],"category_scores_gemma":[0.0001289972,0.0001373218,0.00004971919,0.0004437408,0.00003369716,0.0003096775,0.00008179068,0.00007248077,0.0001664976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005764322,"about_ca_system_score_gemma":0.00002649069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000493446,"about_ca_topic_score_gemma":0.0006494728,"domain_scores_codex":[0.998772,0.00007442115,0.0002395402,0.0004693029,0.0002191587,0.0002256014],"domain_scores_gemma":[0.9987775,0.0007359558,0.00009554604,0.0002300763,0.00007967642,0.00008125202],"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":[0.00006765933,0.00007049637,0.002662882,0.00005058734,0.00003301458,0.000001399676,0.006221891,0.00286687,0.04407493,0.006816362,0.0009692003,0.9361647],"study_design_scores_gemma":[0.001073477,0.00005975811,0.03366746,0.000009653908,0.0000126767,0.000003412616,0.0001494151,0.9599767,0.002702596,0.0006699473,0.001502835,0.0001720831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6475829,0.00001875342,0.3479793,0.00311036,0.0001181739,0.0006526415,0.00000965448,0.0003608134,0.0001674067],"genre_scores_gemma":[0.9788561,0.000008471879,0.01871948,0.0001928251,0.00005940181,0.0001860084,0.0002180928,0.00001718543,0.001742456],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9571098,"threshold_uncertainty_score":0.5599821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03527268440563371,"score_gpt":0.3497033459564788,"score_spread":0.3144306615508451,"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."}}