# Includes an example before and after Jan's naming change.
noelmo-do4-sd1  micro_avg: 0.680, macro_avg: 0.340, mnli_accuracy: 0.680, mnli-diagnostic_accuracy: 0.000, mnli-diagnostic_lex_sem__Morphological negation: 0.413, mnli-diagnostic_lex_sem__Lexical entailment: 0.061, mnli-diagnostic_lex_sem__Quantifiers: 0.349, mnli-diagnostic_lex_sem__Redundancy: 0.693, mnli-diagnostic_lex_sem__Symmetry.Collectivity: 0.000, mnli-diagnostic_lex_sem__Named entities: 0.000, mnli-diagnostic_lex_sem__Factivity: 0.044, mnli-diagnostic_lex_sem__missing: 0.188, mnli-diagnostic_pr_ar_str__Anaphora.Coreference: 0.263, mnli-diagnostic_pr_ar_str__Intersectivity: 0.000, mnli-diagnostic_pr_ar_str__Nominalization: 0.000, mnli-diagnostic_pr_ar_str__Active.Passive: 0.397, mnli-diagnostic_pr_ar_str__Prepositional phrases: 0.181, mnli-diagnostic_pr_ar_str__Genitives.Partitives: 0.687, mnli-diagnostic_pr_ar_str__Core args: 0.125, mnli-diagnostic_pr_ar_str__Relative clauses: 0.188, mnli-diagnostic_pr_ar_str__Coordination scope: 0.204, mnli-diagnostic_pr_ar_str__Restrictivity: -0.146, mnli-diagnostic_pr_ar_str__Datives: 0.556, mnli-diagnostic_pr_ar_str__Ellipsis.Implicits: 0.244, mnli-diagnostic_pr_ar_str__missing: 0.225, mnli-diagnostic_logic__Negation: -0.060, mnli-diagnostic_logic__Conditionals: -0.008, mnli-diagnostic_logic__Double negation: -0.224, mnli-diagnostic_logic__Upward monotone: 0.000, mnli-diagnostic_logic__Downward monotone: 0.117, mnli-diagnostic_logic__Intervals.Numbers: 0.123, mnli-diagnostic_logic__Conjunction: 0.360, mnli-diagnostic_logic__Disjunction: -0.193, mnli-diagnostic_logic__Universal: 0.697, mnli-diagnostic_logic__Existential: 0.249, mnli-diagnostic_logic__Temporal: -0.156, mnli-diagnostic_logic__Non-monotone: -0.057, mnli-diagnostic_logic__missing: 0.120, mnli-diagnostic_knowledge__World knowledge: 0.097, mnli-diagnostic_knowledge__Common sense: 0.150, mnli-diagnostic_knowledge__missing: 0.137
elmo-do4-sd1  micro_avg: 0.000, macro_avg: 0.000, mnli-diagnostic_accuracy: 0.000, mnli-diagnostic_lex_sem__Morphological negation: 0.000, mnli-diagnostic_lex_sem__Lexical entailment: 0.000, mnli-diagnostic_lex_sem__Quantifiers: 0.000, mnli-diagnostic_lex_sem__Redundancy: 0.000, mnli-diagnostic_lex_sem__Symmetry/Collectivity: 0.000, mnli-diagnostic_lex_sem__Named entities: 0.000, mnli-diagnostic_lex_sem__Factivity: 0.000, mnli-diagnostic_lex_sem: 0.000, mnli-diagnostic_pr_ar_str__Anaphora/Coreference: 0.000, mnli-diagnostic_pr_ar_str__Intersectivity: 0.000, mnli-diagnostic_pr_ar_str__Nominalization: 0.000, mnli-diagnostic_pr_ar_str__Active/Passive: 0.000, mnli-diagnostic_pr_ar_str__Prepositional phrases: 0.000, mnli-diagnostic_pr_ar_str__Genitives/Partitives: 0.000, mnli-diagnostic_pr_ar_str__Core args: 0.000, mnli-diagnostic_pr_ar_str__Relative clauses: 0.000, mnli-diagnostic_pr_ar_str__Coordination scope: 0.000, mnli-diagnostic_pr_ar_str__Restrictivity: 0.000, mnli-diagnostic_pr_ar_str__Datives: 0.000, mnli-diagnostic_pr_ar_str__Ellipsis/Implicits: 0.000, mnli-diagnostic_pr_ar_str: 0.000, mnli-diagnostic_logic__Negation: 0.000, mnli-diagnostic_logic__Conditionals: 0.000, mnli-diagnostic_logic__Double negation: 0.000, mnli-diagnostic_logic__Upward monotone: 0.000, mnli-diagnostic_logic__Downward monotone: 0.000, mnli-diagnostic_logic__Intervals/Numbers: 0.000, mnli-diagnostic_logic__Conjunction: 0.000, mnli-diagnostic_logic__Disjunction: 0.000, mnli-diagnostic_logic__Universal: 0.000, mnli-diagnostic_logic__Existential: 0.000, mnli-diagnostic_logic__Temporal: 0.000, mnli-diagnostic_logic__Non-monotone: 0.000, mnli-diagnostic_logic: 0.000, mnli-diagnostic_knowledge__World knowledge: 0.000, mnli-diagnostic_knowledge__Common sense: 0.000, mnli-diagnostic_knowledge: 0.000

