Aflah comments

Results 125 comments of


                                            Aflah

Adding Data Augmentation Techniques Natively

Hi @mattdangerw While I'm working on the other issue too are there any updates on how it's planned to incorporate these DA techniques?

Adding Data Augmentation Techniques Natively

Hey @mattdangerw Thanks for sharing this. Just to confirm this means that these augmentation layers will always be utilized prior to any operations right? Since they take in and return...

Adding Data Augmentation Techniques Natively

There is also this for WordNet - https://wordnet.princeton.edu/download/current-version and the format is here - https://wordnet.princeton.edu/documentation/wndb5wn so we can create our own parser and parse it

Adding Data Augmentation Techniques Natively

Thanks! Should I now get started with some basic ones which are easy to implement such as EDA following the above scheme?

Adding Data Augmentation Techniques Natively

That sounds good. I'll also get to parsing the WordNet data as well and also try out the data in the GitHub release that I had shared

Integrating MLMMaskGenerator into BERT example

@chenmoneygithub Got it! I'll rework on this and test as you said! Thanks for the review!!

Add NLP-specific metrics

@abheesht17 I'd suggest adding perplexity as well as it's one of the trickier metrics to use. Especially since it often gives inconsistent results and hugely varying results (in orders of...

Update README.md

Added Info for Error Faced Due to Versioning Problem

In step 4，”the training file generated in the previous step“ is 0 or 1?

@27182812 @Bhargav5 Hey! Can someone clarify whether the Eval file is the dev file or the test file?

Missing sentiment_test.txt file

For anyone else who faces this leaving the issue open there is no automatic generation of the file it was discussed in another issue the fix is to join the...