by princeton-nlp
Open source · 25k downloads · 28 likes
The *sup-simcse-roberta-large* model is an enhanced version of RoBERTa-large specialized in sentence feature extraction. It generates vector representations (embeddings) of sentences that capture their semantic meaning, enabling precise comparison or classification of texts. Unlike its parent model, it has been fine-tuned using contrastive techniques (SimCSE) on both supervised data (MNLI and SNLI) and unsupervised data (Wikipedia), which improves its ability to distinguish subtle differences in meaning between similar sentences. Its primary use cases include information retrieval, textual similarity detection, document classification, and enhancing dialogue systems. What sets it apart is its robustness in tasks like semantic textual similarity (STS) and its capacity to produce consistent embeddings even for complex or ambiguous sentences.
This model can be used for the task of Feature Extraction
More information needed
The model should not be used to intentionally create hostile or alienating environments for people.
Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
The model craters note in the Github Repository
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).
More information needed
More information needed
The model craters note in the associated paper
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 associated paper (Appendix B) for evaluation details.
More information needed
More information needed
More information needed
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
More information needed
More information needed
More information needed
More information needed
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}
}
More information needed
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!
Princeton NLP group in collaboration with Ezi Ozoani and the Hugging Face team
More information needed
Use the code below to get started with the model.
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("princeton-nlp/sup-simcse-roberta-large")
model = AutoModel.from_pretrained("princeton-nlp/sup-simcse-roberta-large")