|
--- |
|
tags: |
|
- feature-extraction |
|
- bert |
|
--- |
|
|
|
# Model Card for unsup-simcse-bert-large-uncased |
|
|
|
# Model Details |
|
|
|
## Model Description |
|
|
|
More information needed |
|
|
|
- **Developed by:** Princeton NLP group |
|
- **Shared by [Optional]:** Princeton NLP group |
|
|
|
- **Model type:** Feature Extraction |
|
- **Language(s) (NLP):** More information needed |
|
- **License:** More information needed |
|
- **Parent Model:** BERT |
|
- **Resources for more information:** |
|
- [GitHub Repo](https://github.com/princeton-nlp/SimCSE) |
|
- [Associated Paper](https://arxiv.org/abs/2104.08821) |
|
|
|
|
|
# Uses |
|
|
|
|
|
## Direct Use |
|
This model can be used for the task of feature extraction. |
|
|
|
## Downstream Use [Optional] |
|
|
|
More information needed. |
|
|
|
## Out-of-Scope Use |
|
|
|
The model should not be used to intentionally create hostile or alienating environments for people. |
|
|
|
# Bias, Risks, and Limitations |
|
|
|
|
|
Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups. |
|
|
|
|
|
|
|
## Recommendations |
|
|
|
|
|
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. |
|
|
|
# Training Details |
|
|
|
## Training Data |
|
|
|
The model craters note in the [associatedGithub Repository](https://github.com/princeton-nlp/SimCSE/blob/main/README.md): |
|
> We train unsupervised SimCSE on 106 randomly sampled sentences from English Wikipedia, and train supervised SimCSE on the combination of MNLI and SNLI datasets (314k). |
|
|
|
|
|
|
|
## Training Procedure |
|
|
|
|
|
### Preprocessing |
|
|
|
More information needed |
|
|
|
|
|
|
|
### Speeds, Sizes, Times |
|
|
|
|
|
**Hyperparameters** |
|
The model craters note in the [associated GitHub Repo](https://github.com/princeton-nlp/SimCSE) : |
|
|
|
| | Unsup. BERT | Sup. | |
|
|:--------------|:-----------:|:---------:| |
|
| Batch size | 64 | 512 | |
|
| Learning rate (large) | 1e-5 | 1e-5 | |
|
|
|
|
|
|
|
|
|
# Evaluation |
|
|
|
|
|
## Testing Data, Factors & Metrics |
|
|
|
### Testing Data |
|
|
|
The model craters note in the [associated paper](https://arxiv.org/pdf/2104.08821.pdf): |
|
> Our evaluation code for sentence embeddings is based on a modified version of [SentEval](https://github.com/facebookresearch/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 [associated paper](https://arxiv.org/pdf/2104.08821.pdf) (Appendix B) for evaluation details. |
|
|
|
|
|
|
|
### Factors |
|
More information needed |
|
|
|
### Metrics |
|
|
|
More information needed |
|
|
|
|
|
## Results |
|
|
|
More information needed |
|
|
|
|
|
# Model Examination |
|
|
|
The model craters note in the [associated paper](https://arxiv.org/pdf/2104.08821.pdf): |
|
|
|
>**Uniformity and alignment.** |
|
We also observe that (1) though pre-trained embeddings have good alignment, their uniformity is poor (i.e., the embeddings are highly anisotropic); (2) post-processing methods like BERT-flow and BERT-whitening greatly improve uniformity but also suffer a degeneration in alignment; (3) unsupervised SimCSE effectively improves uniformity of pre-trained embeddings whereas keeping a good alignment;(4) incorporating supervised data in SimCSE further amends alignment. |
|
|
|
|
|
|
|
|
|
# Environmental Impact |
|
|
|
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). |
|
|
|
- **Hardware Type:** Nvidia 3090 GPUs with CUDA 11 |
|
- **Hours used:** More information needed |
|
- **Cloud Provider:** More information needed |
|
- **Compute Region:** More information needed |
|
- **Carbon Emitted:** More information needed |
|
|
|
# Technical Specifications [optional] |
|
|
|
## Model Architecture and Objective |
|
|
|
More information needed |
|
|
|
## Compute Infrastructure |
|
|
|
More information needed |
|
|
|
### Hardware |
|
|
|
|
|
More information needed |
|
|
|
### Software |
|
|
|
More information needed. |
|
|
|
# Citation |
|
|
|
|
|
**BibTeX:** |
|
|
|
|
|
```bibtex |
|
@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} |
|
} |
|
``` |
|
|
|
|
|
|
|
|
|
# Glossary [optional] |
|
|
|
More information needed |
|
|
|
# More Information [optional] |
|
More information needed |
|
|
|
|
|
# Model Card Authors [optional] |
|
|
|
Princeton NLP group in collaboration with Ezi Ozoani and the Hugging Face team. |
|
|
|
# Model Card Contact |
|
|
|
If you have any questions related to the code or the paper, feel free to email Tianyu (`[email protected]`) and Xingcheng (`[email protected]`). 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! |
|
|
|
# How to Get Started with the Model |
|
|
|
Use the code below to get started with the model. |
|
|
|
<details> |
|
<summary> Click to expand </summary> |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModel |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("princeton-nlp/unsup-simcse-bert-large-uncased") |
|
|
|
model = AutoModel.from_pretrained("princeton-nlp/unsup-simcse-bert-large-uncased") |
|
``` |
|
</details> |
|
|
|
|
|
|
