SentenceTransformers Documentation¶

SentenceTransformers is a Python framework for state-of-the-art sentence, text and image embeddings. The initial work is described in our paper Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

You can use this framework to compute sentence / text embeddings for more than 100 languages. These embeddings can then be compared e.g. with cosine-similarity to find sentences with a similar meaning. This can be useful for semantic textual similarity, semantic search, or paraphrase mining.

The framework is based on PyTorch and Transformers and offers a large collection of pre-trained models tuned for various tasks. Further, it is easy to fine-tune your own models.

Installation¶

You can install it using pip:

pip install -U sentence-transformers

We recommend Python 3.8 or higher, and at least PyTorch 1.11.0. See installation for further installation options, especially if you want to use a GPU.

Usage¶

The usage is as simple as:

from sentence_transformers import SentenceTransformer
model = SentenceTransformer("all-MiniLM-L6-v2")

# Our sentences to encode
sentences = [
    "This framework generates embeddings for each input sentence",
    "Sentences are passed as a list of string.",
    "The quick brown fox jumps over the lazy dog."
]

# Sentences are encoded by calling model.encode()
embeddings = model.encode(sentences)

# Print the embeddings
for sentence, embedding in zip(sentences, embeddings):
    print("Sentence:", sentence)
    print("Embedding:", embedding)
    print("")

Performance¶

Our models are evaluated extensively and achieve state-of-the-art performance on various tasks. Further, the code is tuned to provide the highest possible speed. Have a look at Pre-Trained Models for an overview of available models and the respective performance on different tasks.

Contact¶

Contact person: Tom Aarsen, tom.aarsen@huggingface.co

Don’t hesitate to open an issue on the repository if something is broken (and it shouldn’t be) or if you have further questions.

This repository contains experimental software and is published for the sole purpose of giving additional background details on the respective publication.

Citing & Authors¶

If you find this repository helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks:

@inproceedings{reimers-2019-sentence-bert,
  title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
  author = "Reimers, Nils and Gurevych, Iryna",
  booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
  month = "11",
  year = "2019",
  publisher = "Association for Computational Linguistics",
  url = "https://arxiv.org/abs/1908.10084",
}

If you use one of the multilingual models, feel free to cite our publication Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation:

@inproceedings{reimers-2020-multilingual-sentence-bert,
  title = "Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation",
  author = "Reimers, Nils and Gurevych, Iryna",
  booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing",
  month = "11",
  year = "2020",
  publisher = "Association for Computational Linguistics",
  url = "https://arxiv.org/abs/2004.09813",
}

If you use the code for data augmentation, feel free to cite our publication Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks:

@inproceedings{thakur-2020-AugSBERT,
  title = "Augmented {SBERT}: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks",
  author = "Thakur, Nandan and Reimers, Nils and Daxenberger, Johannes  and Gurevych, Iryna",
  booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
  month = jun,
  year = "2021",
  address = "Online",
  publisher = "Association for Computational Linguistics",
  url = "https://www.aclweb.org/anthology/2021.naacl-main.28",
  pages = "296--310",
}