Individual explanation for NLP classification
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.
Comments
-
CoreyS Dataiker Alumni, Dataiku DSS Core Designer, Dataiku DSS Core Concepts, Registered Posts: 1,150 ✭✭✭✭✭✭✭✭✭OptionsHi @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. -
Thanks @CoreyS
for pointing it out. The screenshot I had attached earlier, was indeed not visible. I have re-attached it again. -
CoreyS Dataiker Alumni, Dataiku DSS Core Designer, Dataiku DSS Core Concepts, Registered Posts: 1,150 ✭✭✭✭✭✭✭✭✭Options
Thanks for your idea, @RohitRanga
. Your idea meets the criteria for submission, we'll reach out should we require more information. -
Hi all,
I'm interested to know if thers is any update about this request ?
I'v a regression model trained on one column text. I can see the regression coefficient but unfortunatly not able to have this in the detail of an individual explanation since the model give just a global score for the input text withtout mention to how each word impacted this result.
Thanks for your assistance
