Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling

TL;DR

This paper introduces MixEncoder, a lightweight cross-attention mechanism that significantly speeds up sentence pair modeling while maintaining comparable performance to traditional models, enabling faster NLP applications.

Contribution

The paper proposes a novel MixEncoder paradigm with a light-weight cross-attention mechanism for efficient sentence pair modeling.

Findings

Speeds up sentence pair modeling by over 113x

Achieves comparable performance to traditional cross-attention models

Effective across four different NLP tasks

Abstract

Transformer-based models have achieved great success on sentence pair modeling tasks, such as answer selection and natural language inference (NLI). These models generally perform cross-attention over input pairs, leading to prohibitive computational costs. Recent studies propose dual-encoder and late interaction architectures for faster computation. However, the balance between the expressive of cross-attention and computation speedup still needs better coordinated. To this end, this paper introduces a novel paradigm MixEncoder for efficient sentence pair modeling. MixEncoder involves a light-weight cross-attention mechanism. It conducts query encoding only once while modeling the query-candidate interaction in parallel. Extensive experiments conducted on four tasks demonstrate that our MixEncoder can speed up sentence pairing by over 113x while achieving comparable performance as the more expensive cross-attention models.