模型:
cambridgeltl/trans-encoder-bi-simcse-roberta-base
language: en
tags:
由 Liu et al. (2021) 提出的无监督句子编码器(双编码器)。该模型使用从STS2012-2016、STS-b和SICK-R中抽样的未标记的句子对进行训练,使用 princeton-nlp/unsup-simcse-roberta-base 作为基础模型。请将[CLS](在pooler之前)用作输入的表示。
@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} }