Text Matching as Image Recognition

TL;DR

This paper introduces a novel approach to text matching by transforming similarity matrices into images and applying convolutional neural networks to identify complex matching patterns, improving performance over existing methods.

Contribution

It proposes modeling text matching as image recognition using CNNs on similarity matrices, capturing hierarchical matching patterns like n-grams for better accuracy.

Findings

Outperforms baseline methods in text matching tasks

Effectively captures hierarchical matching patterns

Demonstrates the viability of image recognition techniques in NLP

Abstract

Matching two texts is a fundamental problem in many natural language processing tasks. An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score. Inspired by the success of convolutional neural network in image recognition, where neurons can capture many complicated patterns based on the extracted elementary visual patterns such as oriented edges and corners, we propose to model text matching as the problem of image recognition. Firstly, a matching matrix whose entries represent the similarities between words is constructed and viewed as an image. Then a convolutional neural network is utilized to capture rich matching patterns in a layer-by-layer way. We show that by resembling the compositional hierarchies of patterns in image recognition, our model can successfully identify salient signals such as n-gram and n-term matchings. Experimental results demonstrate its superiority against the baselines.