501Good

Coref model skipping long documents during training

3

I have been investigating the code for the coreference model to better understand its inner workings. One thing that caught my attention is that during training documents longer than 5,000...

Discontinuous mentions in the coref model

4

Hello! **Is your feature request related to a problem? Please describe.** Currently, a closing index of a discontinuous mention is not captured by the regex in the [convert_udcoref.py](https://github.com/stanfordnlp/stanza/blob/af3d42b70ef2d82d96f410214f98dd17dd983f51/stanza/utils/datasets/coref/convert_udcoref.py) script. For...