MaartenGr / MaartenGr/BERTopic
find_topics with custom embeddings
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 7.8k
- Forks
- 920
- Avg merge
- 22h 24m
- Merged PRs (30d)
- 5
Description
Hey!
I am working with a dataset of scientific abstracts, so I used SciBERT to generate the embeddings. However, with this, I cannot use the find_topics function to find topics similar to specific keywords I am interested in. I know this is expected behaviour, but I was wondering why is this the case and if there might be any workarounds.
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 examining the find_topics entry point and how it handles custom embeddings such as SciBERT. Determine why keyword-based topic lookup is unsupported and define a reproducible workaround or support path; the issue does not mention specific files or tests.
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