search

MaartenGr / KeyBERT

Minimal keyword extraction with BERT
https://MaartenGr.github.io/KeyBERT/
MIT License
3.47k stars 344 forks source link

type of dataset #164

Closed Hossein-1991 closed 1 year ago

Hossein-1991 commented 1 year ago

Hi,

My question is kind of basic! I would like to use keybert, but I don't know whether removing punctuations are helpful or not! More deeply, are punctuations essential for text classification tasks?

MaartenGr commented 1 year ago

It highly depends on the embedding model that you use. For most transformer-based models, it is important to keep the punctuations as they are part of the context.