hdbscan
sentence-transformers
hdbscan | sentence-transformers | |
---|---|---|
6 | 45 | |
2,675 | 13,842 | |
0.7% | 2.4% | |
5.8 | 9.2 | |
5 days ago | 2 days ago | |
Jupyter Notebook | Python | |
BSD 3-clause "New" or "Revised" License | Apache License 2.0 |
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.
hdbscan
-
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.
- Hierarchical clustering algorithm
-
Introduction to K-Means Clustering
Working in spatial data science, I rarely find applications where k-means is the best tool. The problem is that it is difficult to know how many clusters you can expect on maps. Is it 5, 500, or 10,000? Here HDBSCAN [1] shines because it will cluster _and_ select the most suitable number of clusters, to cut the single linkage cluster tree.
[1]: https://github.com/scikit-learn-contrib/hdbscan
-
New clustering algorithms like DBSCAN and OPTICS?
You might be interested in HDBSCAN which has several implementations, but the python implelementation is commonly used. That implementation makes use of algorithmic changes to significantly improve the computational complexity. Some more recent variations on that include the gamma-linkage variant which is quite powerful.
-
DBSCAN ALternatives?
The OPTICS algorithm is in the latest versions of sklearn and is a reasonable alternative to DBSCAN -- it has much the same theoretical foundation, but can cope with variable density clusters better. If you are willing to step outside sklearn itself there is also HDBSCAN which is a hierarchical clustering version of DBSCAN and is in sklearn-contrib so should be compatible with an sklearn pipeline.
-
[D] Good algorithm for clustering big data (sentences represented as embeddings)?
Maybe use (H)DBScan which I think should work also for huge datasets. I don't think there is a ready to use clustering with unbuild cosine similarily metrics, and you also won't be able to precompute the 100k X 100k dense similarity matrix. The only way to go on this is to L2 normalize your embeddings, then the dot product will be the angular distance as a proxy to the cosine similarily. See also https://github.com/scikit-learn-contrib/hdbscan/issues/69
sentence-transformers
-
External vectorization
txtai is an open-source first system. Given it's own open-source roots, like-minded projects such as sentence-transformers are prioritized during development. But that doesn't mean txtai can't work with Embeddings API services.
-
[D] Looking for a better multilingual embedding model
Ok great. My use case is not very specific, but rather general. I am looking for a model that can perform asymmetric semantic search for the languages I mentioned earlier (Urdu, Persian, Arabic etc.). I have also looked into the sentence-transformer training documentation. Do you think it would be a good idea to use the XNLI dataset for fine-tuning? Or maybe you can suggest much better dataset. Furthermore, I am not sure if fine-tuning is suitable for my task. Because my use case is general so I can use already trained model.
- Best pathway for Domain Adaptation with Sentence Transformers?
-
Syntactic and Semantic surprisal using a LLM
The task you are looking for is semantic textual similarity. There are a few models and datasets out there that can do this. I'd probably start with the SemEval2017 Task 1 task description and competition entries here and then work outward from there (using something like SemanticScholar or Papers With Code to find newer state of the art works that cite these models if needed). For what it's worth you might find that Sentence Bert (SBERT) gives good vectors for cosine similarity comparison out of the box for this task.
-
Mean pooling in BERT
Check out the sentence-transformers implementation. If I don't miss anything they don't exclude CLS when the pooling strategy is set to 'mean'
-
I Built an AI Search Engine that can find exact timestamps for anything on Youtube using OpenAI Whisper
Break up transcript into shorter segments and convert segments to a 768 vector array. Use a process known as embedding using our second ML model, UKP Labs BERT’s sentence transformer model.
-
Seeking advice on improving NLP search results
Not sure what kind of texts you have, but these models have a max sequence limit of 512 (approx 350 words or so). If you're texts are longer than that, consider splitting them up into chunks or creating a summary and taking an embedding of that. Some clustering algorithm may be the way to go here. Here's a bunch of examples. I use agglomerative for my use case.
-
Dev Diary #12 - Finetune model
https://github.com/UKPLab/sentence-transformers/tree/master/examples/training/data_augmentation (Augmented Encoding)
-
[R] Customize size of Bio-BERT pre-trained embeddings
For vector representation you can take the mean and then pca to get the size that you want, but if you have time then use sentence transformers to train a vector representation instead.
- SentenceTransformer producing different sentence embedding results in Docker
What are some alternatives?
faiss - A library for efficient similarity search and clustering of dense vectors.
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Top2Vec - Top2Vec learns jointly embedded topic, document and word vectors.
onnx - Open standard for machine learning interoperability
Milvus - A cloud-native vector database, storage for next generation AI applications
CLIP - CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
100DaysofMLCode - My journey to learn and grow in the domain of Machine Learning and Artificial Intelligence by performing the #100DaysofMLCode Challenge. Now supported by bright developers adding their learnings :+1:
RACplusplus - A high performance implementation of Reciprocal Agglomerative Clustering in C++
txtai - 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
homemade-machine-learning - 🤖 Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained
datasets - 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools