> > > > Which taks do you need to do, APC, ATEPC or ASTE? See the demo https://huggingface.co/spaces/yangheng/PyABSA for details.

[christianjosef27]

          > > > > Which taks do you need to do, APC, ATEPC or ASTE? See the demo https://huggingface.co/spaces/yangheng/PyABSA for details.

I want to do ATEPC. I understand that with this task I can extract 1 or multiple aspect terms and determine their sentiments. I hope I can use my train dataset somehow, otherwise it would be a lot of work to create it again with your provided tool.
Thanks for your help!

***PS: the column "aspect categories" of my train dataset are not a must. I just added them because I might use them later on.

First convert you data to APC format as following (You need to write the code yourself):

Then, convert it to ATEPC dataset: convert_apc_

Okay I see, thank you for those hints! I will try that, however I was wondering the 2 points:

1-So is it true that this way is also a "common way" of doing it/or lets say possible without too big obstacles?
Or is it rather hard to convert my format into the APC format? (I have coding background but not a lot)

2-And the 2. step to convert to ATEPC dataset is basically just using that function of yours right?

Originally posted by @christianjosef27 in #189 (comment)

[yangheng95]

Yes. If you follow the data annotation, this is a simple thing