Giters

marcotcr / sears

Code for "Semantically Equivalent Adversarial Rules for Debugging NLP Models"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

training and creating adversarial examples on another dataset/language

khieu opened this issue · comments

commented

I am interested in trying this method for another dataset at another language other than English. Is there some instruction on how to create such attack?

Thank you so much!

commented

You need a model that can generate paraphrases to replace paraphrase_scorer.py. Also, you won't be able to get rules using POS tags and etc unless you have a POS tagger for that language.