Trans-encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations

In NLP, a large volume of tasks involve pairwise comparison between two sequences (e.g., sentence similarity and paraphrase identification). Predominantly, two formulations are used for sentence-pair tasks: bi-encoders and cross-encoders. Bi-encoders produce fixed-dimensional sentence representations and are computationally efficient, however, they usually underperform cross-encoders. Cross-encoders can leverage their attention heads to exploit inter-sentence interactions for better performance but they require task finetuning and are computationally more expensive. In this paper, we present a completely unsupervised sentence-pair model termed as TRANS-ENCODER that combines the two learning paradigms into an iterative joint framework to simultaneously learn enhanced bi- and cross-encoders. Specifically, on top of a pre-trained language model (PLM), we start with converting it to an unsupervised bi-encoder, and then alternate between the bi- and cross-encoder task formulations. In each alternation, one task formulation will produce pseudo-labels which are used as learning signals for the other task formulation. We then propose an extension to conduct such a self-distillation approach on multiple PLMs in parallel and use the average of their pseudo-labels for mutual distillation. TRANS-ENCODER creates, to the best of our knowledge, the first completely unsupervised cross-encoder and also a state-of-the-art unsupervised bi-encoder for sentence similarity. Both the bi-encoder and cross-encoder formulations of TRANS-ENCODER outperform recently proposed state-of-the-art unsupervised sentence encoders such as Mirror-BERT (Liu et al., 2021) and SimCSE (Gao et al., 2021) by up to 5% on the sentence similarity benchmarks.