2022
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations
ICLR 2022poster
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…