Context-Aware Interaction Network for Question Matching

TL;DR

This paper introduces COIN, a context-aware interaction network that enhances question matching by integrating contextual information into cross-attention mechanisms, leading to improved semantic alignment.

Contribution

The paper proposes a novel context-aware cross-attention mechanism and a gate fusion layer for better sequence alignment in question matching tasks.

Findings

Effective in question matching datasets

Improves semantic alignment accuracy

Refines attention through stacked interaction blocks

Abstract

Impressive milestones have been achieved in text matching by adopting a cross-attention mechanism to capture pertinent semantic connections between two sentence representations. However, regular cross-attention focuses on word-level links between the two input sequences, neglecting the importance of contextual information. We propose a context-aware interaction network (COIN) to properly align two sequences and infer their semantic relationship. Specifically, each interaction block includes (1) a context-aware cross-attention mechanism to effectively integrate contextual information when aligning two sequences, and (2) a gate fusion layer to flexibly interpolate aligned representations. We apply multiple stacked interaction blocks to produce alignments at different levels and gradually refine the attention results. Experiments on two question matching datasets and detailed analyses demonstrate the effectiveness of our model.