Downloads · 30 days
15
0% of all-time downloads
trans-encoder-bi-simcse-roberta-base
cambridgeltl/trans-encoder-bi-simcse-roberta-base
trans-encoder-bi-simcse-roberta-base is a feature extraction model from cambridgeltl. Use it when you need embeddings to search or compare text. It is set up for transformers.
All-time downloads
3.8K
Public
Repo size
997 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin499 MB · 99%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Oct 18, 2021
- SHA
- 6771443b
Model card
From the Hugging Face model README
language: en
tags:
- sentence-embeddings
- sentence-similarity
- dual-encoder
cambridgeltl/trans-encoder-bi-simcse-roberta-base
An unsupervised sentence encoder (bi-encoder) proposed by Liu et al. (2021). The model is trained with unlabelled sentence pairs sampled from STS2012-2016, STS-b, and SICK-R, using princeton-nlp/unsup-simcse-roberta-base as the base model. Please use [CLS] (before pooler) as the representation of the input.
Citation
@article{liu2021trans,
title={Trans-Encoder: Unsupervised sentence-pair modelling through self-and mutual-distillations},
author={Liu, Fangyu and Jiao, Yunlong and Massiah, Jordan and Yilmaz, Emine and Havrylov, Serhii},
journal={arXiv preprint arXiv:2109.13059},
year={2021}
}
- Task
- Feature Extraction
- Library
- transformers
- Type
- roberta
- Created
- Mar 2, 2022
- Updated
- Oct 18, 2021