MaartenGr / MaartenGr/BERTopic
Adding custom topic aspect after training
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 7.8k
- Forks
- 920
- Avg merge
- 22h 24m
- Merged PRs (30d)
- 5
Description
I'm having diffulcties with assigning labels/representatives of topics to the topic_model after training.
I have trained the model and and I happy with the clusters it made. I did not choose the multiple representation or any representation model.
I see the possibilty to update a label per topic and also upload list of topics but this will be updated to column CustomName.
I want to implement multiple representation after the training. Is it possible to apply Generative AI and a custom list of topics under the custom aspects "openai" and "customList"?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing BERTopic's post-training topic representation and custom-aspect APIs, focusing on whether representations can be added after training. Check how the existing CustomName update and multiple-representation options are exposed, then verify whether OpenAI-generated and custom-list aspects can both be attached without retraining.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100