{"id":"W4404781603","doi":"10.18653/v1/2024.mrl-1.28","title":"McGill NLP Group Submission to the MRL 2024 Shared Task: Ensembling Enhances Effectiveness of Multilingual Small LMs","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":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Task (project management); Natural language processing; Artificial intelligence; Group (periodic table); Information retrieval; Engineering","routes":{"ca_aff":false,"ca_fund":true,"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":[0.0146207,0.002994454,0.002963825,0.001883242,0.002415975,0.002814589,0.004492289,0.003437104,0.03112409],"category_scores_gemma":[0.04215849,0.001164596,0.001465714,0.001308753,0.001195147,0.004779026,0.008600516,0.003424715,0.0144311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002174621,"about_ca_system_score_gemma":0.003957653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01970742,"about_ca_topic_score_gemma":0.03738779,"domain_scores_codex":[0.9922357,0.003687255,0.0003754907,0.001821195,0.001309954,0.0005704207],"domain_scores_gemma":[0.9745296,0.01060873,0.0003600342,0.006479964,0.005865795,0.002155961],"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":[0.003463374,0.0009668808,0.00370246,0.0008925528,0.0003688326,0.001124901,0.0008392638,0.02809103,0.03999147,0.002547129,0.5499987,0.3680134],"study_design_scores_gemma":[0.002264543,0.001777064,0.01111977,0.0001717201,0.0002792973,0.0008821947,0.000805578,0.6933139,0.08676913,0.0170407,0.1850355,0.0005406085],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2795075,0.003185846,0.3707612,0.01152609,0.008211777,0.003788339,0.04278821,0.2268283,0.05340275],"genre_scores_gemma":[0.506016,0.000401653,0.3123868,0.002228486,0.001150705,0.002406014,0.1017848,0.01519541,0.05843011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03112409,"threshold_uncertainty_score":0.1041204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0180914597200848,"score_gpt":0.2973023893340466,"score_spread":0.2792109296139618,"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."}}