{"id":"W2159755860","doi":"","title":"Batch Tuning Strategies for Statistical Machine Translation","year":2012,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":338,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"Johns Hopkins University","keywords":"Computer science; Machine translation; Machine learning; Feature (linguistics); Artificial intelligence; Variety (cybernetics); Support vector machine; Translation (biology); Simple (philosophy); Sentence; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002268787,0.00006764475,0.00007267568,0.00003755415,0.00006788864,0.0001108381,0.0002570978,0.00003892442,0.00003023377],"category_scores_gemma":[0.00002869063,0.00005715702,0.00001890774,0.00009119035,0.00001928016,0.0007610732,0.00002950597,0.0000816062,0.000004074841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002063042,"about_ca_system_score_gemma":0.00002879142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007364206,"about_ca_topic_score_gemma":0.000004900045,"domain_scores_codex":[0.999437,0.00002201036,0.00009607559,0.0001174672,0.0001180682,0.0002093506],"domain_scores_gemma":[0.9996212,0.0001272798,0.00002847975,0.0001386783,0.00003303124,0.00005134638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003658226,0.00001345412,0.00006438707,0.00001962563,0.000002272177,5.644524e-7,0.0004639021,3.759114e-7,0.007006436,0.6991587,0.0005720076,0.2926946],"study_design_scores_gemma":[0.0002025691,0.00006673827,0.0001121552,0.00001956291,0.000008087804,0.00001222892,0.00005142514,0.2005158,0.01017001,0.7862135,0.002432074,0.000195903],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002033625,0.0006531744,0.9948072,0.0006903452,0.00009178645,0.0001047739,0.000009230253,0.000327194,0.003112932],"genre_scores_gemma":[0.4839375,8.329714e-7,0.515929,0.00005473134,0.00003762374,0.00001039236,0.000007446178,0.00000345445,0.00001903889],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4837342,"threshold_uncertainty_score":0.2330796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02839738380637398,"score_gpt":0.3112397182538902,"score_spread":0.2828423344475162,"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."}}