neuralmonkey.evaluators.f1_bio module¶
-
class
neuralmonkey.evaluators.f1_bio.F1Evaluator(name: str = None) → None¶ Bases:
neuralmonkey.evaluators.evaluator.EvaluatorF1 evaluator for BIO tagging, e.g. NP chunking.
The entities are annotated as beginning of the entity (B), continuation of the entity (I), the rest is outside the entity (O).
-
static
chunk2set() → Set[str]¶
-
score_instance(hypothesis: List[str], reference: List[str]) → float¶ Score a single hyp/ref pair.
The default implementation of this method returns 1.0 when the hypothesis and the reference are equal and 0.0 otherwise.
Parameters: - hypothesis – The model prediction.
- reference – The golden output.
Returns: A float.
-
static