add weak span based f1 metric #32
Open
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds
SpanBasedF1WeakMeasuremetric. TheSpanBasedF1WeakMeasureimplements span-based precision, recall and F1 measure for different tagging (encoding) schemes. A span can either have exact match (strict) or it can be partially overlapped (weak) with predicted span. This metric allows both strict and weak version with the help of a boolean parameterweak. The concept of weak and strict span overlap is described in Lauscher et al. (2018).This metric can handle multiple encoding schemes (available here) using a parameter called
label_encoding. Finally, this metric can retrieve not only the F1 measure but precision and recall as well. Using a parameter calledreturn_metric, we can specify if we want the metric for each tag or averaged over all tags.