Michele Bevilacqua

icon indicating a website link mbevila.github.io icon indicating an email [email protected]

icon location Rome, Italy icon location Trying to teach human language to machines, one failure at a time. Ex @facebookresearch. Ex @SapienzaNLP. Topics: NLP, NLG, Lexical Semantics, Semantic Parsin

Results 3 comments of Michele Bevilacqua

Hyperparameters not the same in paper and config

Hi, I am not sure what is happening here. We have retrained SPRING several times and we have always reproduced the same results, up to some variation due to the...

Hyperparameters not the same in paper and config

For more context, here's what the training curves look like for us.

What do you mean by WordNet offset?

Hi, 1) The offsets are the unique IDs that are assigned to synsets (groups of senses). EWISER performs classification at the synset level, and that's why we output WN offsets....