Matt Watson
Matt Watson
@Stealth-py would you like to take a look at this too? It might make sense to work on in tandem with https://github.com/keras-team/keras-nlp/issues/114
@Stealth-py thanks!
No worries at all! Figured this would be sequential after #114 Thanks for all the work here.
@Stealth-py hey! Few things here... First, just FYI, we had a big bug in our finetuning script where we would output logits to a loss that was expecting softmax probs...
Yeah, maybe we do something like this... - Remove to `do_evaluation` flag. If the test data has real labels run evaluate automatically, if not skip. - Add an `output_tsv_file` flag....
@aflah02 thanks! And yes +1 to opening issues for specific layers like this, rather than the "catch all" issues.
Will take a look next Monday!
@aflah02 a few questions... - Would this parser require pandas? Could we avoid the dependency with https://docs.python.org/3/library/csv.html ? - Where's the best documentation for what the wordnet file format looks...
> This is something I've been thinking about too and the best i can think of right now is we could support json dumps so essentially two dumps one telling...
Another key question, how does the EDA implemtation and others handle stemming and lemmatization? E.g. finding a synonym for "hats" vs "hat" or "runs" vs "running".