{"id":"W4404780584","doi":"10.18653/v1/2024.wmt-1.7","title":"MSLC24 Submissions to the General Machine Translation Task","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":"National Research Council Canada","funders":"","keywords":"Computer science; Machine translation; Task (project management); Translation (biology); Natural language processing; Artificial intelligence; Information retrieval; Engineering; Systems engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.009488415,0.004519048,0.003140148,0.003463614,0.002697795,0.00462621,0.002632885,0.003618909,0.04780697],"category_scores_gemma":[0.03595531,0.0008084617,0.0019622,0.003596043,0.001277414,0.002504409,0.00705226,0.003334277,0.04723853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002123968,"about_ca_system_score_gemma":0.003727631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006494041,"about_ca_topic_score_gemma":0.01605294,"domain_scores_codex":[0.986221,0.005225176,0.001017366,0.001758227,0.00464537,0.001132801],"domain_scores_gemma":[0.9749956,0.003980323,0.0006299905,0.005988429,0.01096388,0.003441961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005841692,0.0001859742,0.0003773486,0.0006223031,0.000131517,0.0002834845,0.0001444436,0.001684114,0.004088953,0.0008571766,0.9483174,0.04272311],"study_design_scores_gemma":[0.001610553,0.001406801,0.007799956,0.0002284991,0.0001494754,0.001437308,0.0008540175,0.02945917,0.02050296,0.01065199,0.9255773,0.0003219013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1230747,0.006367753,0.08163395,0.009800438,0.04232526,0.006001576,0.4376493,0.1441713,0.1489756],"genre_scores_gemma":[0.07288031,0.0006685894,0.05512486,0.001840213,0.002566008,0.003275598,0.7596931,0.01593596,0.0880154],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04780697,"threshold_uncertainty_score":0.1599303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01663518745428682,"score_gpt":0.3038602543352716,"score_spread":0.2872250668809848,"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."}}