MaartenGr / MaartenGr/BERTopic
Zero Shot Topic ordering
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 7.8k
- Forks
- 920
- Avg merge
- 22h 24m
- Merged PRs (30d)
- 5
Description
### Have you searched existing issues? 🔎
- [x] I have searched and found no existing issues
### Desribe the bug
I predefined the zero shot topic list, but the ordering of the topics is not the same as the list i provided:
```python
zeroshot_topic_list = [
'Technology & Science',
'Arts Culture',
'Business',
'International',
'Geo Politics',
'Health & Wellness',
'Sports',
'Opinion & Editorial',
'Education',
'Environment',
]
topic_model = BERTopic(
language='english',
embedding_model="thenlper/gte-large",
min_topic_size=15,
zeroshot_topic_list=zeroshot_topic_list,
zeroshot_min_similarity=0,
calculate_probabilities=True,
representation_model=KeyBERTInspired()
)
topics, props = topic_model.fit_transform(docs)
```
### Reproduction
```python
from bertopic import BERTopic
zeroshot_topic_list = [
'Technology & Science',
'Arts Culture',
'Business',
'International',
'Geo Politics',
'Health & Wellness',
'Sports',
'Opinion & Editorial',
'Education',
'Environment',
]
topic_model = BERTopic(
language='english',
embedding_model="thenlper/gte-large",
min_topic_size=15,
zeroshot_topic_list=zeroshot_topic_list,
zeroshot_min_similarity=0,
calculate_probabilities=False,
representation_model=KeyBERTInspired()
)
topics, props = topic_model.fit_transform(docs)
```
### BERTopic Version
0.17.0
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 running the provided BERTopic reproduction with the zero-shot topic list and inspect how fit_transform handles zero-shot topics and their returned ordering. The issue is resolved when the resulting topic ordering follows the supplied zeroshot_topic_list; the payload does not name a source file or test.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100