sentence-transformers
Top2Vec
Our great sponsors
sentence-transformers | Top2Vec | |
---|---|---|
45 | 13 | |
13,793 | 2,843 | |
4.5% | - | |
9.2 | 7.0 | |
2 days ago | 5 months ago | |
Python | Python | |
Apache License 2.0 | BSD 3-clause "New" or "Revised" 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.
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
Top2Vec
-
[D] Is it better to create a different set of Doc2Vec embeddings for each group in my dataset, rather than generating embeddings for the entire dataset?
I'm using Top2Vec with Doc2Vec embeddings to find topics in a dataset of ~4000 social media posts. This dataset has three groups:
-
Tips for best Top2Vec (HDBSCAN) usage
I asked in a previous post for advice about how to find insight in unstructured text data. Almost everyone recommended BERTopic, but I wasn't able to run BERTopic on my machine locally (segmentation fault). Fortunately, I found Top2Vec, which uses HBDSCAN and UMAP to quickly find good topics in uncleaned(!) text data.
- 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.
- Top2Vec: Embed topics, documents and word vectors
- How to cluster articles about software vulnerabilities?
- Ciencia de Dados - Classificacao de texto
-
Extracting topics from 250k facebook posts
Since you already have the facebook posts, you can use top2vec https://github.com/ddangelov/Top2Vec
- [D] Good algorithm for clustering big data (sentences represented as embeddings)?
-
SOTA for Topic Modeling
Here's an implementation that uses UMAP and HDBSCAN: https://github.com/ddangelov/Top2Vec but you could use a semi-supervised algorithm in the clustering step if you wanted specific topics.
What are some alternatives?
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
BERTopic - Leveraging BERT and c-TF-IDF to create easily interpretable topics.
onnx - Open standard for machine learning interoperability
faiss - A library for efficient similarity search and clustering of dense vectors.
CLIP - CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Milvus - A cloud-native vector database, storage for next generation AI applications
txtai - 💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
hdbscan - A high performance implementation of HDBSCAN clustering.
datasets - 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
GuidedLDA - semi supervised guided topic model with custom guidedLDA
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.