VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction
This addresses efficiency and performance issues in text matching for NLP applications, but it is incremental as it builds on existing Siamese encoder methods.
The paper tackled the performance degradation of representation-based text matching models due to lack of interaction between text pairs by proposing VIRT, a virtual interaction mechanism that transfers interactive knowledge from interaction-based models through attention map distillation, achieving state-of-the-art results on multiple datasets.
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 interaction-based models into Siamese encoders through attention map distillation. As a train-time-only component, VIRT could completely maintain the high efficiency of the Siamese structure and brings no extra computation cost during inference. To fully utilize the learned interactive knowledge, we further design a VIRT-adapted interaction strategy. Experimental results on multiple text matching datasets demonstrate that our method outperforms state-of-the-art representation-based models. What's more, VIRT can be easily integrated into existing representation-based methods to achieve further improvements.