Nikita Kitaev

Also python 3.9.2 is less than a week old, so I wouldn't be surprised if the torch ecosystem has some issues with it. Actually I just did a search for...

As far as I can tell, this is an issue with pytorch-struct (https://github.com/harvardnlp/pytorch-struct), and I don't see any way to suppress the warning from the benepar side. The warning is...

The 300-word limit is inherent to the pre-trained model; it can't be changed without modifying the model. There are multiple places in the model architecture that place a limit on...

BERT has an inherent length limit of 512 sub-word tokens, so you can only raise the limit from 300 words to 512 sub-words before you hit a limit that requires...

I posted treebank conversion scripts at https://github.com/nikitakit/parser-data-gen These scripts are able to recover the gold-tag data format I have directly from the LDC release. When it comes to EVALB errors,...

I added a CTB processing script as well: https://github.com/nikitakit/parser-data-gen/blob/master/corpora/ctb_5.1/build_corpus.sh You'll have to change the reference to `${HOME}/data/ctb_5.1/` to instead point to the right location on your machine.

Would extracting the CKY-style parse charts work for you?

Hydrogen allows connecting multiple files to the same kernel. You can put functions/classes in one file, and use the other for more exploratory code. You can also log in to...

Did you have any `print` statements inside the loop? I know that if you print output fast enough, Atom will hang because it can't keep up with displaying the messages....

Sorry, it looks like I missed the notifications for this issue. You can look at the `svg2sif_compare` script in this repo for an example of how to run the converter...