1
$\begingroup$

I am new to machine learning and NLP.

I am exploring the possibility of using one of these approaches to automatically examine a large collection of text documents and determine, first of all, if they talk about funding opportunities for small-medium enterprises.

Then, considering only the matching documents, I would need to automatically understand the (1) (who is providing the funding), the (2) what kind of business is being funded, the (3) how (how many funds), the (4) when (the deadline for applying), as well as other information of this kind.

Do you have any idea about what kind of automated approach, if any, can be pursued to this end?

Improve this question
$\endgroup$

2 Answers 2

Reset to default
1
$\begingroup$

I can only answer your first part, if you want to automatically label document if they are talking about funding opportunities, you can train a classification model to classify which document belong to your defined class and which is not. But to train such a model, you need data, and in your data you have to define and label manually documents that belong to your class of interest and documents that do not as examples to your model.

Improve this answer
$\endgroup$
1
  • $\begingroup$ Thanks for your suggestion, @Hal, fortunately I have several examples of documents belonging to the different classes of documents $\endgroup$
    – ProjK
    Nov 28, 2021 at 15:50
1
$\begingroup$

I agree that the first part is text classification. The last part looks like a Named Entity Recognition problem: detect specific types of words or sequences of words in a document among several possible categories. It would also require training a model using some annotated data.

Improve this answer
$\endgroup$
2
  • $\begingroup$ Thank you, @Erwan, do you know of any library that can be used to solve the NER problem? $\endgroup$
    – ProjK
    Nov 28, 2021 at 15:51
  • $\begingroup$ @ProjK yep, there are many, see for example this question. All these libraries use CRF, which is the state of the art method for sequence labeling (that's the name for this type of problem). Mind that using these methods requires a good bit of learning. $\endgroup$
    – Erwan
    Nov 28, 2021 at 17:03

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.