ConllCorefScores(self) -> None
ConllCorefScores.get_metric(self, reset:bool=False) -> Tuple[float, float, float]
Compute and return the metric. Optionally also call :func:
Reset any accumulators or internal state.
Mostly borrowed from https://github.com/clarkkev/deep-coref/blob/master/evaluation.py
Averaged per-mention precision and recall. https://pdfs.semanticscholar.org/cfe3/c24695f1c14b78a5b8e95bcbd1c666140fd1.pdf
Counts the mentions in each predicted cluster which need to be re-allocated in order for each predicted cluster to be contained by the respective gold cluster. https://aclweb.org/anthology/M/M95/M95-1005.pdf
Subroutine for ceafe. Computes the mention F measure between gold and predicted mentions in a cluster.
Computes the Constrained EntityAlignment F-Measure (CEAF) for evaluating coreference. Gold and predicted mentions are aligned into clusterings which maximise a metric - in this case, the F measure between gold and predicted clusters.