{"id":"W3117912976","doi":"10.18653/v1/2020.semeval-1.32","title":"UAlberta at SemEval-2020 Task 2: Using Translations to Predict Cross-Lingual Entailment","year":2020,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"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":"Leverage (statistics); Computer science; Textual entailment; Logical consequence; Natural language processing; SemEval; Artificial intelligence; Task (project management); Word (group theory); Linguistics","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":[0.00361579,0.001639503,0.0009891273,0.002949636,0.001628465,0.002490943,0.001270022,0.002131112,0.01893384],"category_scores_gemma":[0.01105377,0.0004730983,0.0009855584,0.001707705,0.0005732846,0.003003776,0.002367202,0.00173477,0.01340187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001306899,"about_ca_system_score_gemma":0.001668201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01863246,"about_ca_topic_score_gemma":0.0387264,"domain_scores_codex":[0.9975121,0.0009124159,0.0001821056,0.0006737043,0.0005623859,0.0001573723],"domain_scores_gemma":[0.9960453,0.001294103,0.0002778545,0.0009789653,0.001102547,0.0003012219],"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":[0.004165897,0.001554873,0.02182702,0.00139875,0.000521231,0.001321131,0.0006309507,0.01382956,0.01922096,0.008235448,0.4942893,0.4330049],"study_design_scores_gemma":[0.001950196,0.001542951,0.07190728,0.0007489196,0.000524919,0.002707294,0.001865009,0.3611932,0.07825108,0.03002797,0.4489342,0.0003469291],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5741653,0.01115337,0.08402567,0.005498969,0.003571288,0.001062817,0.2021802,0.03160069,0.08674159],"genre_scores_gemma":[0.4825585,0.001086049,0.1029343,0.001026782,0.0004118322,0.0006742544,0.3693212,0.001912384,0.04007482],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01893384,"threshold_uncertainty_score":0.06334001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02719183343376473,"score_gpt":0.3227681545403572,"score_spread":0.2955763211065924,"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."}}