{"id":"W6891660818","doi":"10.48448/0r09-t174","title":"Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Machine translation; Similarity (geometry); Domain (mathematical analysis); Focus (optics); Translation (biology); Natural language; Language model","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002265465,0.0003948843,0.0003415902,0.000814769,0.0002319675,0.0001177825,0.001208068,0.0002086149,0.0004103265],"category_scores_gemma":[0.000109271,0.0002664202,0.00009864523,0.0016327,0.001357609,0.0001506543,0.0001506925,0.0007911814,0.0009505356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001647363,"about_ca_system_score_gemma":0.0002543887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003599479,"about_ca_topic_score_gemma":0.0006765076,"domain_scores_codex":[0.9966487,0.0001140436,0.0004286214,0.000753082,0.001527728,0.0005277666],"domain_scores_gemma":[0.9984478,0.0001295909,0.0003767688,0.0008773629,0.00006147203,0.0001069659],"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":[0.0008136112,0.002649284,0.01548132,0.005108993,0.0009638398,0.000105976,0.04679614,0.02328612,0.1460629,0.02729768,0.1540718,0.5773624],"study_design_scores_gemma":[0.000880387,0.0004229648,0.0003339145,0.00298646,0.0002182904,0.00003086524,0.003791883,0.5342654,0.007285195,0.001627129,0.4471588,0.000998744],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.01439876,0.005521737,0.0003088129,0.0003225258,0.0003070061,0.001042734,0.0009363572,0.0008554212,0.9763067],"genre_scores_gemma":[0.9599205,0.00004090578,0.002547691,0.0001954179,0.0007049053,0.00002908988,0.0001535077,0.0009071737,0.03550078],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9455218,"threshold_uncertainty_score":0.9999788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0122021436285633,"score_gpt":0.2735886007659061,"score_spread":0.2613864571373428,"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."}}