Detecting cognitive impairments by agreeing on interpretations of linguistic features

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 handcrafting 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.

Examining the rhetorical capacities of neural language models

“…Tree property features (Tree) We compute the depth and the Yngve depth (the number of rightbranching in the tree) (Yngve, 1960) of each tree node, and include their mean and variance as characteristic features, following previous work extracting tree linguistic features (Li et al, 2019;Zhu et al, 2019).…”

Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power

“…Prior research reports the utility of different modalities of speech -lexical and syntactic (Bucks et al, 2000;Noorian et al, 2017;Zhu et al, 2019) Similarly, varying feature sets have been used for detecting aphasia from speech. Researchers have studied the importance of syntactic complexity indicators such as Yngve-depth and length of various syntactic representations for detecting aphasia (Roark et al, 2011), as well as lexical characteristics such as average frequency and the imageability of words used (Bird et al, 2000).…”

Impact of ASR on Alzheimer’s Disease Detection: All Errors are Equal, but Deletions are More Equal than Others

“…Machine learning (ML) models have proved to be successful in detecting AD using speech and language variables, such as syntactic and lexical complexity of language extracted from the transcripts of the speech Meilán et al, 2012;Rentoumi et al, 2014). Since transcripts should be accurate enough to properly represent syntactic and linguistic characteristics, current approaches (Fraser et al, 2013;Zhu et al, 2019) frequently rely on 100% accurate human-created transcripts produced by trained transcriptionists. However in real-life speech-based applications of AD detection, ASR is used and it produces noisy, error-prone transcripts (Yousaf et al, 2019).…”