Open j0ma opened 1 year ago
Posting this here as well, originally from #2 :
Both models trained for 20 epochs using 1xV100 GPU with update_freq=4
, i.e. training with delayed updates simulating 4xGPUs.
SER Accuracy Language
0.163 27.983 multi
Halving the learning rate seems to bring gains
SER Accuracy Language
0.139 31.326 multi
After training Nada's model for 20 epochs (like in her paper) this is what we get
When we take a random German sentence from the dev set, the model does quite well:
Clearly there are some mistakes like
s/n/m/g
but overall the performance is remarkably good.The model is also able to handle just a little chunk of the sentence:
However the model is quite brittle. If we think up a random sentence that is not taken from the development data but is nevertheless similar to the sentence above, we get pseudo-Swedish output:
When we use a sentence whose syntax is a bit closer to the dev sentence, the model fares better. At least the output is now pseudo-German.
When we modify the sentence to be a bit more "Yiddish-like" (
konnte
is not valid Yiddish), the output degrades substantially:What's cool to notice is that the model does pick up on
(aber, ober)
and(was,vos)
.