Pauses for Detection of Alzheimer’s Disease

Abstract

Pauses, disfluencies and language problems in Alzheimer’s disease can be naturally modeled by fine-tuning Transformer-based pre-trained language models such as BERT and ERNIE. Using this method with pause-encoded transcripts, we achieved 89.6% accuracy on the test set of the ADReSS (Alzheimer’sDementiaRecognition throughSpontaneousSpeech) Challenge. The best accuracy was obtained with ERNIE, plus an encoding of pauses. Robustness is a challenge for large models and small training sets. Ensemble over many runs of BERT/ERNIE fine-tuning reduced variance and improved accuracy. We found thatumwas used much less frequently in Alzheimer’s speech, compared touh. We discussed this interesting finding from linguistic and cognitive perspectives.