Hi,
I have data that has two fields, "text", and "label". Of my dataset, about 50% of it is already annotated with accurate "label" lines. For example, my data may look like:
| Text | Label |
|------|-------|
| Apple unveils new iPhone 15 Pro with titanium design and USB-C port | iPhone 15 Pro |
| Microsoft announces Windows 11 update with enhanced AI chatbot features | Windows 11|
| Google releases Pixel 8 smartphone with improved night vision camera | Pixel 8 |
| Tesla launches Cybertruck with stainless steel exoskeleton and tri-motor AWD | Cybertruck |
Would it be possible to train some sort of model to automatically extract the other 50% of fields? From the looks of it, the [Splunk App for Data Science and Deep Learning](https://splunkbase.splunk.com/app/4607) seems roughly like what I would want, but I want to double check before going down this path.
