Text Matching as Image Recognition
This approach addresses a fundamental problem in natural language processing for tasks requiring text comparison, but it is incremental as it adapts an existing method from image recognition.
The paper tackled text matching by modeling it as image recognition, using a convolutional neural network on a similarity matrix to capture matching patterns, and demonstrated superior performance against baselines.
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.