{"id":"W2154417380","doi":"","title":"Fast Consensus Hypothesis Regeneration for Machine Translation","year":2010,"lang":"en","type":"article","venue":"NPARC","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":"NIST; Machine translation; Computer science; Decoding methods; Regeneration (biology); Task (project management); Translation (biology); Artificial intelligence; Natural language processing; Baseline (sea); Algorithm; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003518777,0.001459026,0.00145601,0.002470021,0.001815212,0.001340101,0.002574076,0.002017037,0.009867731],"category_scores_gemma":[0.01046663,0.0007954756,0.001263594,0.002105874,0.001210533,0.003224324,0.00266131,0.00236465,0.007284476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007987958,"about_ca_system_score_gemma":0.001982415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002140007,"about_ca_topic_score_gemma":0.002756376,"domain_scores_codex":[0.9965345,0.001310699,0.0002050567,0.0007252669,0.0009986811,0.0002257544],"domain_scores_gemma":[0.990355,0.005558668,0.0004784084,0.001587476,0.001831329,0.0001890937],"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":[0.0007805299,0.0001938358,0.0009063644,0.0004915082,0.0001598797,0.0005232334,0.0003663866,0.05445702,0.03847216,0.01543144,0.01653678,0.8716809],"study_design_scores_gemma":[0.000156791,0.0002987513,0.0005458352,0.00004281218,0.00008165764,0.0005682805,0.0002030298,0.8429396,0.07461283,0.0670288,0.01342049,0.0001011916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007312008,0.0004136189,0.9836096,0.0001610708,0.00008980257,0.0001030692,0.0002068742,0.006831243,0.001272719],"genre_scores_gemma":[0.2027446,0.0002881542,0.7886535,0.0002636118,0.0001431899,0.0003999768,0.002186337,0.001058445,0.004262255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009867731,"threshold_uncertainty_score":0.03301084,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02168418839725299,"score_gpt":0.2625955019507148,"score_spread":0.2409113135534618,"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."}}