We need to propose an NLP pipeline. That is, we need to start thinking about what packages we use, what functions might come in handy and have a general outline of how data will be processed.
Deliverable:
List of packages we want to/are going to use
A pipeline:
list of steps needed to take
list of functions/methods/techniques we will use for each step
Have defined inputs and outputs of the pipeline
Suggested list of potential features we want to build
We can list these things in this ticket as a comment. A "completed" ticket, will have all of the things outlined above in one, or multiple comments. The more complete the comments the better.
On top of this, we ideally will also create small modules with which we can draft basic final versions of certain modules. That is, we should write code for this additional requirement.
Deliverable:
Write a Python file (jupyter or otherwise) that can analyze a tex/data field of your choice
We need to propose an NLP pipeline. That is, we need to start thinking about what packages we use, what functions might come in handy and have a general outline of how data will be processed.
Deliverable:
We can list these things in this ticket as a comment. A "completed" ticket, will have all of the things outlined above in one, or multiple comments. The more complete the comments the better.