to_nervaluate()

Documents in nervaluate-disco’s span format, one dict per document.

Usage

Source

to_nervaluate(
    docs,
    *,
    unlabelled="raise",
)

Pass gold and predicted documents in the same order::

from nervaluate import Evaluator
true = cane.to_nervaluate(gold_docs)
pred = cane.to_nervaluate(result.document for result in results)
Evaluator(true, pred, tags=labels).evaluate()

Parameters

docs: Iterable[Document]

The documents.

unlabelled: Literal["raise", "skip"] = "raise"

Entities without a label cannot be evaluated: "raise" or "skip".