readme example fixes

README.md

@@ -53,9 +53,46 @@ result = metric.compute(dataset=dataset["test"], model_id="gpt2")
 
 # Compute suite accuracy. Mean success over items, where "success" is the conjunction
 # of all boolean prediction results.
-suite_accuracies = [np.array(suite_results["prediction_results"]).all(axis=1).mean(axis=0)
-                    for suite_results in result.values()]
-overall_accuracy = np.mean(suite_accuracies.values())
+suite_accuracies = {suite_name: np.array(suite_results["prediction_results"]).all(axis=1).mean(axis=0)
+                    for suite_name, suite_results in result.items()}
+overall_accuracy = np.mean(list(suite_accuracies.values()))
+```
+
+```python
+>>> suite_accuracies
+{'center_embed': 0.9285714285714286,
+ 'center_embed_mod': 0.8571428571428571,
+ 'cleft': 1.0,
+ 'cleft_modifier': 0.925,
+ 'fgd_hierarchy': 0.0,
+ 'fgd_object': 0.9583333333333334,
+ 'fgd_pp': 0.875,
+ 'fgd_subject': 0.5,
+ 'mvrr': 0.7857142857142857,
+ 'mvrr_mod': 0.75,
+ 'npi_orc_any': 0.9736842105263158,
+ 'npi_orc_ever': 1.0,
+ 'npi_src_any': 0.5789473684210527,
+ 'npi_src_ever': 0.9210526315789473,
+ 'npz_ambig': 0.9166666666666666,
+ 'npz_ambig_mod': 0.875,
+ 'npz_obj': 1.0,
+ 'npz_obj_mod': 1.0,
+ 'number_orc': 0.631578947368421,
+ 'number_prep': 0.7894736842105263,
+ 'number_src': 0.7894736842105263,
+ 'reflexive_orc_fem': 0.47368421052631576,
+ 'reflexive_orc_masc': 0.8421052631578947,
+ 'reflexive_prep_fem': 0.21052631578947367,
+ 'reflexive_prep_masc': 0.7894736842105263,
+ 'reflexive_src_fem': 0.15789473684210525,
+ 'reflexive_src_masc': 0.631578947368421,
+ 'subordination': 1.0,
+ 'subordination_orc-orc': 1.0,
+ 'subordination_pp-pp': 1.0,
+ 'subordination_src-src': 1.0}
+>>> overall_accuracy
+0.7793839437302936
 ```
 
 ### Inputs