MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification

TL;DR

This paper presents MGNC-CNN, a simple and efficient CNN architecture that leverages multiple word embeddings for improved sentence classification, outperforming existing models with less training time.

Contribution

The paper introduces MGNC-CNN, a novel CNN model that independently processes multiple word embeddings and applies group regularization, offering a simpler and faster alternative to existing methods.

Findings

MGNC-CNN outperforms baseline models in sentence classification tasks.

The model requires less training time than comparable architectures.

It is flexible with input embeddings of different dimensions.

Abstract

We introduce a novel, simple convolution neural network (CNN) architecture - multi-group norm constraint CNN (MGNC-CNN) that capitalizes on multiple sets of word embeddings for sentence classification. MGNC-CNN extracts features from input embedding sets independently and then joins these at the penultimate layer in the network to form a final feature vector. We then adopt a group regularization strategy that differentially penalizes weights associated with the subcomponents generated from the respective embedding sets. This model is much simpler than comparable alternative architectures and requires substantially less training time. Furthermore, it is flexible in that it does not require input word embeddings to be of the same dimensionality. We show that MGNC-CNN consistently outperforms baseline models.