VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction. (arXiv:2112.04195v2 [cs.CL] UPDATED)

With the booming of pre-trained transformers, representation-based models
based on Siamese transformer encoders have become mainstream techniques for
efficient text matching. However, these models suffer from severe performance
degradation due to the lack of interaction between the text pair, compared with
interaction-based models. Prior arts attempt to address this through performing
extra interaction for Siamese encoded representations, while the interaction
during encoding is still ignored. To remedy this, we propose a \textit{Virtual}
InteRacTion mechanism (VIRT) to transfer interactive knowledge from …

arxiv representation text virtual