implementations of models and metrics for semantic text similarity. that's it.
an easy-to-use interface to fine-tuned BERT models for computing semantic similarity. that's it.
This project contains an interface to fine-tuned, BERT-based semantic text similarity models. It modifies pytorch-transformers by abstracting away all the research benchmarking code for ease of real-world applicability.
|Model||Training Dataset||Dev. Correlation|
|Web STS BERT||STS-B||0.893|
|Clinical STS BERT||MED-STS|
Install with pip:
pip install semantic-text-similarity
pip install git+https://github.com/AndriyMulyar/semantic-text-similarity
Maps batches of sentence pairs to real-valued scores in the range [0,5]
from semantic_text_similarity.models import WebBertSimilarity model = WebBertSimilarity(device='cpu', batch_size=10) #defaults to GPU prediction model.predict([("She won an olympic gold medal","The women is an olympic champion")])
- You will need a GPU to apply these models if you would like any hint of speed in your predictions.
- Model downloads are cached in
~/.cache/torch/semantic_text_similarity/. Try clearing this folder if you have issues.
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size semantic_text_similarity-1.0.1-py3-none-any.whl (414.7 kB)||File type Wheel||Python version py3||Upload date||Hashes View hashes|
|Filename, size semantic_text_similarity-1.0.1.tar.gz (409.5 kB)||File type Source||Python version None||Upload date||Hashes View hashes|
Hashes for semantic_text_similarity-1.0.1-py3-none-any.whl
Hashes for semantic_text_similarity-1.0.1.tar.gz