Individual explanation for NLP classification

[RohitRanga]

It would be very useful to know why a model classified a particular text into a particular class(es), for e.g., the model made this decision because of so and so tokens/words/phrases. Refer attachment. 

The challenge would be to have this feature even if I use, for e.g. Universal Sentence Encoder (for feature extraction) and SVM for classification, where the classifier does not have access to the tokens seen during training.  

 

[CoreyS]

Hi @RohitRanga thank you for submitting your idea. Just to be clear in your idea you mention to refer to an attachment. I just want to be sure that you aren't missing anything visually in presenting your idea. If not, then I apologize in advance for misunderstanding an element of your idea.

[RohitRanga]

Thanks @CoreyS for pointing it out. The screenshot I had attached earlier, was indeed not visible. I have re-attached it again.

[CoreyS]

Thanks for your idea, @RohitRanga. Your idea meets the criteria for submission, we'll reach out should we require more information.