An Experimental Analysis of Multi-Perspective Convolutional Neural Networks

Abstract

Modelling the similarity of sentence pairs is an important problem in natural language processing and information retrieval, with applications in tasks such as paraphrase identification and answer selection in question answering. The Multi-Perspective Convolutional Neural Network (MP-CNN) is a model that improved previous state-of-the-art models in 2015 and has remained a popular model for sentence similarity tasks. However, until now, there has not been a rigorous study of how the model actually achieves competitive accuracy. In this thesis, we report on a series of detailed experiments that break down the contribution of each component of MP-CNN towards its statistical accuracy and how they affect model robustness. We find that two key components of MP-CNN are non-essential to achieve competitive accuracy and they make the model less robust to changes in hyperparameters. Furthermore, we suggest simple changes to the architecture and experimentally show that we improve the accuracy of MP-CNN when we remove these two major components of MP-CNN and incorporate these small changes, pushing its scores closer to more recent works on competitive semantic textual similarity and answer selection datasets, while using eight times fewer parameters.