“TSDAE: Using Transformer-Based Sequential Denoising Autoencoder for Unsupervised Sentence Embedding Learning”, Kexin Wang, Nils Reimers, Iryna Gurevych2021-04-14 (retrieval AI, Transformer, autoencoder NN)⁠:

Learning sentence embeddings often requires a large amount of labeled data. However, for most tasks and domains, labeled data is seldom available and creating it is expensive. In this work, we present a new state-of-the-art unsupervised method based on pre-trained Transformers and Sequential Denoising Autoencoder (TSDAE) which outperforms previous approaches by up to 6.4 points. It can achieve up to 93.1% of the performance of in-domain supervised approaches. Further, we show that TSDAE is a strong domain adaptation and pre-training method for sentence embeddings, outperforming other approaches like Masked Language Model.

A crucial shortcoming of previous studies is the narrow evaluation: Most work mainly evaluates on the single task of Semantic Textual Similarity (STS), which does not require any domain knowledge. It is unclear if these proposed methods generalize to other domains and tasks. We fill this gap and evaluate TSDAE and other recent approaches on 4 different datasets from heterogeneous domains.