Home

Awesome

SimCSE: Simple Contrastive Learning of Sentence Embeddings

This repository contains the code and pre-trained models for our paper SimCSE: Simple Contrastive Learning of Sentence Embeddings.

**************************** Updates ****************************

<!-- Thanks for your interest in our repo! --> <!-- Probably you will think this as another *"empty"* repo of a preprint paper 🥱. Wait a minute! The authors are working day and night 💪, to make the code and models available, so you can explore our state-of-the-art sentence embeddings. We anticipate the code will be out * **in one week** *. --> <!-- * 4/26: SimCSE is now on [Gradio Web Demo](https://gradio.app/g/AK391/SimCSE) (Thanks [@AK391](https://github.com/AK391)!). Try it out! -->

Quick Links

Overview

We propose a simple contrastive learning framework that works with both unlabeled and labeled data. Unsupervised SimCSE simply takes an input sentence and predicts itself in a contrastive learning framework, with only standard dropout used as noise. Our supervised SimCSE incorporates annotated pairs from NLI datasets into contrastive learning by using entailment pairs as positives and contradiction pairs as hard negatives. The following figure is an illustration of our models.

Getting Started

We provide an easy-to-use sentence embedding tool based on our SimCSE model (see our Wiki for detailed usage). To use the tool, first install the simcse package from PyPI

pip install simcse

Or directly install it from our code

python setup.py install

Note that if you want to enable GPU encoding, you should install the correct version of PyTorch that supports CUDA. See PyTorch official website for instructions.

After installing the package, you can load our model by just two lines of code

from simcse import SimCSE
model = SimCSE("princeton-nlp/sup-simcse-bert-base-uncased")

See model list for a full list of available models.

Then you can use our model for encoding sentences into embeddings

embeddings = model.encode("A woman is reading.")

Compute the cosine similarities between two groups of sentences

sentences_a = ['A woman is reading.', 'A man is playing a guitar.']
sentences_b = ['He plays guitar.', 'A woman is making a photo.']
similarities = model.similarity(sentences_a, sentences_b)

Or build index for a group of sentences and search among them

sentences = ['A woman is reading.', 'A man is playing a guitar.']
model.build_index(sentences)
results = model.search("He plays guitar.")

We also support faiss, an efficient similarity search library. Just install the package following instructions here and simcse will automatically use faiss for efficient search.

WARNING: We have found that faiss did not well support Nvidia AMPERE GPUs (3090 and A100). In that case, you should change to other GPUs or install the CPU version of faiss package.

We also provide an easy-to-build demo website to show how SimCSE can be used in sentence retrieval. The code is based on DensePhrases' repo and demo (a lot of thanks to the authors of DensePhrases).

Model List

Our released models are listed as following. You can import these models by using the simcse package or using HuggingFace's Transformers.

ModelAvg. STS
princeton-nlp/unsup-simcse-bert-base-uncased76.25
princeton-nlp/unsup-simcse-bert-large-uncased78.41
princeton-nlp/unsup-simcse-roberta-base76.57
princeton-nlp/unsup-simcse-roberta-large78.90
princeton-nlp/sup-simcse-bert-base-uncased81.57
princeton-nlp/sup-simcse-bert-large-uncased82.21
princeton-nlp/sup-simcse-roberta-base82.52
princeton-nlp/sup-simcse-roberta-large83.76

Note that the results are slightly better than what we have reported in the current version of the paper after adopting a new set of hyperparameters (for hyperparamters, see the training section).

Naming rules: unsup and sup represent "unsupervised" (trained on Wikipedia corpus) and "supervised" (trained on NLI datasets) respectively.

Use SimCSE with Huggingface

Besides using our provided sentence embedding tool, you can also easily import our models with HuggingFace's transformers:

import torch
from scipy.spatial.distance import cosine
from transformers import AutoModel, AutoTokenizer

# Import our models. The package will take care of downloading the models automatically
tokenizer = AutoTokenizer.from_pretrained("princeton-nlp/sup-simcse-bert-base-uncased")
model = AutoModel.from_pretrained("princeton-nlp/sup-simcse-bert-base-uncased")

# Tokenize input texts
texts = [
    "There's a kid on a skateboard.",
    "A kid is skateboarding.",
    "A kid is inside the house."
]
inputs = tokenizer(texts, padding=True, truncation=True, return_tensors="pt")

# Get the embeddings
with torch.no_grad():
    embeddings = model(**inputs, output_hidden_states=True, return_dict=True).pooler_output

# Calculate cosine similarities
# Cosine similarities are in [-1, 1]. Higher means more similar
cosine_sim_0_1 = 1 - cosine(embeddings[0], embeddings[1])
cosine_sim_0_2 = 1 - cosine(embeddings[0], embeddings[2])

print("Cosine similarity between \"%s\" and \"%s\" is: %.3f" % (texts[0], texts[1], cosine_sim_0_1))
print("Cosine similarity between \"%s\" and \"%s\" is: %.3f" % (texts[0], texts[2], cosine_sim_0_2))

If you encounter any problem when directly loading the models by HuggingFace's API, you can also download the models manually from the above table and use model = AutoModel.from_pretrained({PATH TO THE DOWNLOAD MODEL}).

Train SimCSE

In the following section, we describe how to train a SimCSE model by using our code.

Requirements

First, install PyTorch by following the instructions from the official website. To faithfully reproduce our results, please use the correct 1.7.1 version corresponding to your platforms/CUDA versions. PyTorch version higher than 1.7.1 should also work. For example, if you use Linux and CUDA11 (how to check CUDA version), install PyTorch by the following command,

pip install torch==1.7.1+cu110 -f https://download.pytorch.org/whl/torch_stable.html

If you instead use CUDA <11 or CPU, install PyTorch by the following command,

pip install torch==1.7.1

Then run the following script to install the remaining dependencies,

pip install -r requirements.txt

Evaluation

Our evaluation code for sentence embeddings is based on a modified version of SentEval. It evaluates sentence embeddings on semantic textual similarity (STS) tasks and downstream transfer tasks. For STS tasks, our evaluation takes the "all" setting, and report Spearman's correlation. See our paper (Appendix B) for evaluation details.

Before evaluation, please download the evaluation datasets by running

cd SentEval/data/downstream/
bash download_dataset.sh

Then come back to the root directory, you can evaluate any transformers-based pre-trained models using our evaluation code. For example,

python evaluation.py \
    --model_name_or_path princeton-nlp/sup-simcse-bert-base-uncased \
    --pooler cls \
    --task_set sts \
    --mode test

which is expected to output the results in a tabular format:

------ test ------
+-------+-------+-------+-------+-------+--------------+-----------------+-------+
| STS12 | STS13 | STS14 | STS15 | STS16 | STSBenchmark | SICKRelatedness |  Avg. |
+-------+-------+-------+-------+-------+--------------+-----------------+-------+
| 75.30 | 84.67 | 80.19 | 85.40 | 80.82 |    84.26     |      80.39      | 81.58 |
+-------+-------+-------+-------+-------+--------------+-----------------+-------+

Arguments for the evaluation script are as follows,

Training

Data

For unsupervised SimCSE, we sample 1 million sentences from English Wikipedia; for supervised SimCSE, we use the SNLI and MNLI datasets. You can run data/download_wiki.sh and data/download_nli.sh to download the two datasets.

Training scripts

We provide example training scripts for both unsupervised and supervised SimCSE. In run_unsup_example.sh, we provide a single-GPU (or CPU) example for the unsupervised version, and in run_sup_example.sh we give a multiple-GPU example for the supervised version. Both scripts call train.py for training. We explain the arguments in following:

All the other arguments are standard Huggingface's transformers training arguments. Some of the often-used arguments are: --output_dir, --learning_rate, --per_device_train_batch_size. In our example scripts, we also set to evaluate the model on the STS-B development set (need to download the dataset following the evaluation section) and save the best checkpoint.

For results in the paper, we use Nvidia 3090 GPUs with CUDA 11. Using different types of devices or different versions of CUDA/other softwares may lead to slightly different performance.

Hyperparameters

We use the following hyperparamters for training SimCSE:

Unsup. BERTUnsup. RoBERTaSup.
Batch size64512512
Learning rate (base)3e-51e-55e-5
Learning rate (large)1e-53e-51e-5

Convert models

Our saved checkpoints are slightly different from Huggingface's pre-trained checkpoints. Run python simcse_to_huggingface.py --path {PATH_TO_CHECKPOINT_FOLDER} to convert it. After that, you can evaluate it by our evaluation code or directly use it out of the box.

Bugs or questions?

If you have any questions related to the code or the paper, feel free to email Tianyu (tianyug@cs.princeton.edu) and Xingcheng (yxc18@mails.tsinghua.edu.cn). If you encounter any problems when using the code, or want to report a bug, you can open an issue. Please try to specify the problem with details so we can help you better and quicker!

Citation

Please cite our paper if you use SimCSE in your work:

@inproceedings{gao2021simcse,
   title={{SimCSE}: Simple Contrastive Learning of Sentence Embeddings},
   author={Gao, Tianyu and Yao, Xingcheng and Chen, Danqi},
   booktitle={Empirical Methods in Natural Language Processing (EMNLP)},
   year={2021}
}

SimCSE Elsewhere

We thank the community's efforts for extending SimCSE!