Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Provide NER identification #344

Closed
tianchiguaixia opened this issue Oct 31, 2023 · 1 comment
Closed

Provide NER identification #344

tianchiguaixia opened this issue Oct 31, 2023 · 1 comment
Labels
feat/task Feature: tasks usage How to use `spacy-llm`

Comments

@tianchiguaixia
Copy link

Indeed, this can solve some NER problems. How to target those parts that cannot be extracted?

  1. Is there a method for fine tuning provided

  2. Is a knowledge base provided

@rmitsch rmitsch added feat/task Feature: tasks usage How to use `spacy-llm` labels Oct 31, 2023
@rmitsch
Copy link
Collaborator

rmitsch commented Oct 31, 2023

Hi @tianchiguaixia,

  • spacy-llm doesn't provide any tools for fine-tuning LLMs. For that, I recommend looking into the capabilities of the provider you're using (OpenAI, Anthropic, Cohere, ...) or, correspondingly, open source tools (e. g. here).
  • A knowledge base is not part of the NER task, no.

I recommend tackling this by combining the LLM NER task with an EntityRuler to leverage a rule-based approach if you have prior knowledge about the entities in your data and/or a pretrained spaCy NER (non-LLM) component. This should help catch entities not identified by your LLM.

@rmitsch rmitsch closed this as completed Jan 29, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
feat/task Feature: tasks usage How to use `spacy-llm`
Projects
None yet
Development

No branches or pull requests

2 participants