{"id":"W2251810465","doi":"","title":"Improving AMBER, an MT Evaluation Metric","year":2012,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Metric (unit); Computer science; Task (project management); Machine translation; Translation (biology); Simplex; Artificial intelligence; Algorithm; Pattern recognition (psychology); Mathematics; Chemistry; Combinatorics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001138996,0.00007756313,0.00007104527,0.0001533647,0.00007451679,0.0001165753,0.0005255227,0.00005221866,0.00005739972],"category_scores_gemma":[0.0002379689,0.0000661452,0.0000225764,0.0005385579,0.00001277196,0.001673062,0.0001518979,0.0001124913,0.00002667229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007795815,"about_ca_system_score_gemma":0.00004444261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002222467,"about_ca_topic_score_gemma":0.000001381929,"domain_scores_codex":[0.9989737,0.0000862412,0.0001059359,0.0001839005,0.0004037608,0.0002464188],"domain_scores_gemma":[0.999283,0.00003508238,0.00007236464,0.0003996895,0.0001213735,0.00008849311],"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":[9.78783e-7,0.00003860926,0.0002649422,0.0000077052,0.000002203527,0.000001102192,0.0003517665,5.10789e-7,0.06529756,0.02589617,0.000346327,0.9077922],"study_design_scores_gemma":[0.0005105977,0.0001942895,0.002227384,0.0000350442,0.00004892239,0.0001318106,0.00004198676,0.4536941,0.3075646,0.2333048,0.00151713,0.0007292618],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01813389,0.00187921,0.9715011,0.0001738385,0.0003741526,0.0001913494,4.781451e-7,0.0007663566,0.006979595],"genre_scores_gemma":[0.5619914,0.000001112323,0.4377662,0.0001047524,0.00008513812,0.00001134492,0.000001301545,0.000004059432,0.00003473483],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9070629,"threshold_uncertainty_score":0.2697323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02691899758865522,"score_gpt":0.3156656344312011,"score_spread":0.2887466368425459,"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."}}