Detecting cognitive impairments by agreeing on interpretations of linguistic features

TL;DR

This paper introduces Consensus Networks, a novel framework that improves detection of cognitive impairments by aligning representations of linguistic features from different modalities, outperforming traditional classifiers.

Contribution

The paper proposes Consensus Networks that classify based on agreement between modality-specific neural representations, reducing the need for extensive data or handcrafted features.

Findings

Models with all 413 features outperform traditional classifiers.

Consensus Networks achieve significant accuracy improvements.

Ablation studies confirm the importance of modality division.

Abstract

Linguistic features have shown promising applications for detecting various cognitive impairments. To improve detection accuracies, increasing the amount of data or the number of linguistic features have been two applicable approaches. However, acquiring additional clinical data can be expensive, and hand-crafting features is burdensome. In this paper, we take a third approach, proposing Consensus Networks (CNs), a framework to classify after reaching agreements between modalities. We divide linguistic features into non-overlapping subsets according to their modalities, and let neural networks learn low-dimensional representations that agree with each other. These representations are passed into a classifier network. All neural networks are optimized iteratively. In this paper, we also present two methods that improve the performance of CNs. We then present ablation studies to illustrate the effectiveness of modality division. To understand further what happens in CNs, we visualize the representations during training. Overall, using all of the 413 linguistic features, our models significantly outperform traditional classifiers, which are used by the state-of-the-art papers.