Joan Codina

If I use new vocabulary, can I initialize the it's embeddings using the average obtained from their subword parts? And how can I introduce it in the model?

Strange behavior with alignment and transformers. In the following text , and changing it a bit, the error disappears, the word "dog" in the second sentence, is aligned with two...

The Ġ I don't care. I think is part of the tokenizer, i did not check You should realize that dog has two parts [11, 12] while speed has also...

Hi @adrianeboyd, I think i can survive with this strange punctual issue, but when it comes to longer sentences the parts seem totally broken. It seems (please correct me if...

Hi thanks for the fast answer, but this was not my question ;-) My idea is I'm presenting something on a web page, and using Gromit to do some annotations....

Yes! maybe that's the best way to express it. ! And I see that you label it as feature request .

Hi @alexklibisz First thanks for fast response, and the plug-in itself!! let me apologize , for sending the pull request before deeply testing it. It's my first time doing things...

hi. @alexklibisz my company doesn't want to use it. So, I will finish it out-hours I'll do my best with exceptions and testing.

@alexklibisz Now I'm back with this code, I wanted to extract some logs, let me see If I can finish it

Hi, @alexklibisz , I added some tests (i normalized the vectors for dot product) and also I rebased the branch to main I can't compile it, because there is an...