OCTIS
BERTopic
OCTIS | BERTopic | |
---|---|---|
7 | 22 | |
685 | 5,564 | |
1.0% | - | |
6.0 | 8.2 | |
4 months ago | 7 days ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
OCTIS
-
Interpretation of topic modeling results between LDA and BERTopic
OCTIS
-
(NLP) Best practices for topic modeling and generating interesting topics?
My team and I have recently released a python library called OCTIS (https://github.com/mind-Lab/octis) that allows you to automatically optimize the hyperparameters of a topic model according to a given evaluation metric (not log-likelihood). I guess, in your case, you might be interested in topic coherence. So you will get good quality topics with a low effort on the choice of the hyperparameters. Also, we included some state-of-the-art topic models, e.g. contextualized topic models (https://github.com/MilaNLProc/contextualized-topic-models).
-
I am working on a topic modelling paper and I need your help
I recently released a topic modeling library that also includes different evaluation measures. If you are interested, I leave here the link: https://github.com/mind-Lab/octis
-
Latest trends in topic modelling?
Silvia Terragni (a coauthor on the above) also brought a topic modelling library OCTIS which was exhibited as a demo paper and aims to be the huggingface transformers of topic modelling - it includes wrappers around the above model as well as and LDA and some baselines as well as some tools and frameworks for comparing them.
-
OCTIS a python framework to compare and optimize Topic Models
Link to the code Paper
- OCTIS, our new python framework to optimize and compare topic models has been accepted at EACL2021!
- [p] OCTIS: Optimizing and Comparing Topic models Is Simple. Our new python framework to compare and optimize topic models using Bayesian Optimization
BERTopic
-
how can a top2vec output be improved
Try experimenting with different hyperparameters, clustering algorithms and embedding representations. Try https://github.com/MaartenGr/BERTopic/tree/master/bertopic
-
SBERT Embeddings from Conversations
Try out this notebook which comes with the BERTopic repository.
-
Sentence transformers (BERTopic) on a Macbook Air
After some googling, I found this (but for M1 chip Mac) --I wonder if I'm stuck. Is this laptop just not up for the job of working with sentence transformers? Appreciate your advice
-
Comparing BERTopic to human raters
Most has already been said and I am not sure how relevant this is but since you are focusing on human raters it might be worthwhile to mention that there is a Pull Request in BERTopic that allows you to use models on top of the default pipeline that further fine-tunes the topic representation. In theory, this would allow you to even use ChatGPT or any of the other OpenAI models to label the topics. From a human annotator perspective, this might be interesting to pursue.
-
text clustering with XLNET, ROBERTA, ELMO and other pretrained models
The BERTopic library allows you to plug and play any type of embedding.
- How can I group domain specific keywords based on their word embeddings?
-
Introducing the Semantic Graph
A number of excellent topic modeling libraries exist in Python today. BERTopic and Top2Vec are two of the most popular. Both use sentence-transformers to encode data into vectors, UMAP for dimensionality reduction and HDBSCAN to cluster nodes.
-
Classifying unstructured text: sentences, phrases, lists of words
BERTopic is a library to consider if you want something that groups data by topic.
-
[D] How to best extract product benefits/problems from customer reviews using NLP?
I have experimented a bit with BERTopic but didn't find the results very useful. The issue is, that it is very important what exactly people are liking or disliking about the products, not just the fact that they are talking about specific aspects.
- Classify texts using known categories, NLP
What are some alternatives?
contextualized-topic-models - A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021.
Top2Vec - Top2Vec learns jointly embedded topic, document and word vectors.
auto-sklearn - Automated Machine Learning with scikit-learn
gensim - Topic Modelling for Humans
image-similarity-measures - :chart_with_upwards_trend: Implementation of eight evaluation metrics to access the similarity between two images. The eight metrics are as follows: RMSE, PSNR, SSIM, ISSM, FSIM, SRE, SAM, and UIQ.
GuidedLDA - semi supervised guided topic model with custom guidedLDA
SMAC3 - SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
TopMost - A Topic Modeling System Toolkit
PyABSA - Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;
scattertext - Beautiful visualizations of how language differs among document types.
clip-as-service - 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP