Irene

multilingual bert-training size

1

Hi, could you please specify how large is the training size of the multilingual version of BERT, in terms of GB? Thanks

--log-file option with rasa shell nlu

1

### What problem are you trying to solve? It is possible to redirect the output of rasa shell nlu to an output file? This is possible for rasa shell with...

Bert-ita-xxl

4

Hi, could you please specify in what percentage Wikipedia, the OPUS and the OSCAR corpus were used for training ita-bert-xxl? Thanks

spacy tokenizer

1

Hi, the spacy tokenizer in the NLU module (specifically, jointBERT) is downloaded every time the script is launched? Thus, the module downloads the latest version of the tokenizer? Or the...

evaluate vs test

5

Hi, it's not clear the difference between the evaluate.py and test.py scripts in the NLU folder. What do they evaluate? Since the result obtained is completely different even if they...

RULEDST evaluation

9

Hi, could you please provide more information on how the Rule DST module is evaluated? Thanks

Hi, I have a question about the training set of AlBERTo. I've read that the pre-trained lower cased model is based on 200M of tweets (191GB of raw data) but...