{"id":"W4401043678","doi":"10.18653/v1/2024.semeval-1.254","title":"UAlberta at SemEval-2024 Task 1: A Potpourri of Methods for Quantifying Multilingual Semantic Textual Relatedness and Similarity","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"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; Potpourri; Natural language processing; Semantic similarity; Task (project management); Similarity (geometry); Artificial intelligence; Information retrieval; Botany","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.0168535,0.004300268,0.003162628,0.01118601,0.004826061,0.00675363,0.004419134,0.005933271,0.02106545],"category_scores_gemma":[0.04119593,0.001223777,0.002359821,0.004464477,0.001780456,0.01394513,0.01224768,0.004376918,0.01948629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00290638,"about_ca_system_score_gemma":0.003431425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02162936,"about_ca_topic_score_gemma":0.02639215,"domain_scores_codex":[0.9788247,0.01259734,0.001474224,0.003086704,0.003256127,0.0007610189],"domain_scores_gemma":[0.9743852,0.01345424,0.0008259871,0.004859538,0.004944574,0.001530483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003420117,0.001911498,0.007067672,0.003364708,0.0008981252,0.0007821808,0.002180902,0.003273122,0.01350099,0.008136854,0.5868326,0.3686313],"study_design_scores_gemma":[0.003479647,0.001519871,0.03507345,0.00173658,0.001046745,0.002553252,0.01031375,0.2215892,0.04573609,0.04457562,0.6315573,0.0008184388],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.2581706,0.02543213,0.2219124,0.0105177,0.00700441,0.007760738,0.2700672,0.1036736,0.09546115],"genre_scores_gemma":[0.2336954,0.001556048,0.2083211,0.001822399,0.0006881066,0.005489226,0.5096047,0.007685127,0.03113792],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02162936,"threshold_uncertainty_score":0.08913088,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05256413189295486,"score_gpt":0.411826296017001,"score_spread":0.3592621641240462,"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."}}