End-to-End Multi-View Networks for Text Classification

TL;DR

This paper introduces a multi-view network architecture for text classification that automatically generates diverse attention-based views of input text, leading to improved accuracy and robustness.

Contribution

It presents a novel multi-view architecture that stacks and concatenates attention-based views, achieving state-of-the-art results in text classification.

Findings

Achieved new state-of-the-art accuracy on benchmark datasets.

Demonstrated robustness through diverse attention views.

Enabled faster training convergence.

Abstract

We propose a multi-view network for text classification. Our method automatically creates various views of its input text, each taking the form of soft attention weights that distribute the classifier's focus among a set of base features. For a bag-of-words representation, each view focuses on a different subset of the text's words. Aggregating many such views results in a more discriminative and robust representation. Through a novel architecture that both stacks and concatenates views, we produce a network that emphasizes both depth and width, allowing training to converge quickly. Using our multi-view architecture, we establish new state-of-the-art accuracies on two benchmark tasks.