{"id":"W2010856309","doi":"10.1155/2012/484580","title":"Learning to Translate: A Statistical and Computational Analysis","year":2012,"lang":"en","type":"article","venue":"Advances in Artificial Intelligence","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Phrase; Zipf's law; Machine translation; Algorithmic learning theory; Artificial intelligence; Inference; Natural language processing; Statistical inference; Machine learning; Point (geometry); Active learning (machine learning); Mathematics","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":[0.006485973,0.000740149,0.0009898499,0.002383468,0.0009678219,0.002184818,0.001241051,0.0009613017,0.006109584],"category_scores_gemma":[0.0625427,0.0004275491,0.0008624109,0.003229137,0.001672622,0.005373746,0.001748293,0.00189503,0.001133343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001486802,"about_ca_system_score_gemma":0.001489359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002841419,"about_ca_topic_score_gemma":0.002928207,"domain_scores_codex":[0.9960427,0.001774356,0.0002236228,0.0004776244,0.001306637,0.0001750842],"domain_scores_gemma":[0.914305,0.07552568,0.001678025,0.00571712,0.002492854,0.0002812339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004744181,0.0005839247,0.0164351,0.0006865155,0.0001899729,0.0003073914,0.0004699746,0.4319003,0.008130557,0.1749606,0.01154974,0.3543115],"study_design_scores_gemma":[0.00001447384,0.00008904805,0.002746558,0.00001996443,0.00001830066,0.0001519358,0.00007799226,0.9363288,0.003196989,0.05568709,0.001646844,0.00002201942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2083133,0.002621566,0.7644739,0.004571254,0.0001554146,0.000258133,0.001437849,0.001769262,0.01639944],"genre_scores_gemma":[0.7407311,0.001133096,0.2511401,0.0004431775,0.0002590361,0.0006293794,0.002437994,0.0004523306,0.002773774],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006485973,"threshold_uncertainty_score":0.03430152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02152639447210036,"score_gpt":0.3633712533238113,"score_spread":0.3418448588517109,"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."}}