Closed RishabhMaheshwary closed 4 years ago
Hi, here are the answers:
So, Are you not counting the queries to the target model during word ranking step ?
Actually any time that involves querying the model for the probability vector, I counted it in, which includes the word ranking step.
Ok, Thanks.
I have doubt from the word replacement section of the paper.
Are you querying the target model for every synonym of a word (selected after POS and semantic similarity check) and than selecting the synonym with least confidence score, and than repeating the process for each word in the text ordered by their classification drop score ?
How are you calculating the no. of queries to the model ?