John Bauer
John Bauer
The variants page uses one color palette, such as red for [22C(Omicron)](https://covariants.org/variants/22C.Omicron) (BA2.12.1), reddish orange for [22B(Omicron)](https://covariants.org/variants/22B.Omicron) (BA.5), etc. The graphs use a different color scheme, though, such as dark...
Would you be up for adding a `reduction=...` option which allows for sum vs mean?
Actually, it's not clear what the result should be, but it's causing the depparse to get super slow ``` nlp = stanza.Pipeline('ta') doc = nlp('. . . . . ....
example: most common: `'s_VERB` can be either `is` or `has` less likely, but still possible: `wound_VERB` can be `wound` or `wind` `bound`, `found` as well
Make very fine grained models out of this data? https://semeval.github.io/SemEval2023/
English Stanza (1.5.0 beta) labels "August House" as a date, not an org (the publisher) or a facility (the building in South Africa)
Hi, I am wondering, have you tried any of the German-specific transformer options available on HF? For example https://huggingface.co/google-bert/bert-base-german-cased https://huggingface.co/dbmdz/bert-base-german-cased (or uncased) https://huggingface.co/german-nlp-group/electra-base-german-uncased In my experiments, I generally find the...
Stanza maintainer from across the bay. We have a constituency parser which is doing pretty well, but I am not sure what evaluation to use to match the leaderboard scores....
I have a relatively large tensor I'd like to visualize, multiple iterations of a 2048x3292 tensor. When I use `save` on a list of 4 of these tensors, the image...
I've been building a parser where the goal is to read multiple objects from the same file (trees from a Penn Treebank style parser dataset, in case that helps). Currently...