{"id":"W2121771196","doi":"","title":"AMBER: A Modified BLEU, Enhanced Ranking Metric","year":2011,"lang":"en","type":"article","venue":"NPARC","topic":"Topic Modeling","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"BLEU; Metric (unit); Computer science; Machine translation; Ranking (information retrieval); Artificial intelligence; Natural language processing; Sentence; Consistency (knowledge bases); Task (project management); Recall; Translation (biology); Speech recognition; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002328432,0.00009447882,0.0001259216,0.0001467487,0.0000660855,0.00004785456,0.000725298,0.0000470897,0.0001260969],"category_scores_gemma":[0.00004242826,0.0000887287,0.00005097656,0.0004501335,0.00001474921,0.0002763525,0.0001991216,0.0001076476,0.00009649575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002865284,"about_ca_system_score_gemma":0.0000348962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000036866,"about_ca_topic_score_gemma":0.000003634787,"domain_scores_codex":[0.99897,0.00003618746,0.0001724172,0.0003215864,0.0002334459,0.0002664016],"domain_scores_gemma":[0.9992097,0.0000398598,0.00005645262,0.0005791539,0.00004590032,0.00006890701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001597486,0.0001058073,0.0001825062,0.00002411332,0.00003930051,0.00003268599,0.006895342,0.0003774643,0.05912383,0.490705,0.0004226647,0.4420753],"study_design_scores_gemma":[0.001112139,0.00009067023,0.001311004,0.00004213622,0.00001731455,0.00001916248,0.0000365757,0.5909947,0.165612,0.239338,0.0008806699,0.0005455384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0486263,0.0000272574,0.7855176,0.00006637414,0.0002680304,0.00007128881,1.674553e-7,0.0001622436,0.1652607],"genre_scores_gemma":[0.7914293,0.000004898304,0.2079776,0.0001617745,0.00004360358,0.00001070436,1.591103e-7,0.000005575223,0.0003663417],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.742803,"threshold_uncertainty_score":0.3618251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04939886284340537,"score_gpt":0.2435130355547379,"score_spread":0.1941141727113325,"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."}}