language: en
tags:
- sentence-embeddings
- sentence-similarity
cambridgeltl/mirror-bert-base-uncased-sentence-drophead
An unsupervised sentence encoder proposed by Liu et al. (2021), using drophead instead of dropout as feature space augmentation. Trained with unlabelled raw sentences, using bert-base-uncased as the base model. Please use mean-pooling over all tokens as the representation of the input.
Note the model does not replicate the exact numbers in the paper since the reported numbers in the paper are average of three runs.
Citation
@inproceedings{
liu2021fast,
title={Fast, Effective and Self-Supervised: Transforming Masked LanguageModels into Universal Lexical and Sentence Encoders},
author={Liu, Fangyu and Vuli{\'c}, Ivan and Korhonen, Anna and Collier, Nigel},
booktitle={EMNLP 2021},
year={2021}
}