Evaluation treats multiple categories too leniently

[danielhers]

Evaluation is by spans, and if there is a non-empty intersection of the categories, then the span is considered correct. This is a problem because parsers can just predict many unary edges or multi-category edges and not be penalized for it: https://github.com/danielhers/ucca/blob/master/ucca/evaluation.py#L102
@omriabnd @nschneid

[nschneid]

One subtlety is that, because F nodes are moved under the root, we are left with superfluous C nodes:

[F The] [H [P [C service] ] ... [D poor] [U ...] ] [F is]

Should they be removed? I.e.:

[F The] [H [P service ] ... [D poor] [U ...] ] [F is]

Scoring P and C separately here (in an edge-based evaluation) would seem inconsistent with the notion of ignoring where F attaches.

[danielhers]

Yes, I think normalization (including C-flattening) should occur again after moving Fs.

[nschneid]

Should moving all Fs be part of normalization? For structures like [S [F the] [C xyz]] it would make it more transparent that xyz is evoking a scene.

[nschneid]

Also: the confusion matrix code should match the F-score computation