What are some recommended pretrained models for extracting semantic feature on single sentence?

Seems like you are looking for the Sentence Transformers library which trains Siamese BERT (etc.) networks on NLI data. That means that you can indeed pass one sentence to get a sentence embedding. They also have a few finetuned models that use cross-encoders instead. Those are obviously slower but lead to better performance on downstream tasks such as STSb.

3 Likes