Improved POS tagging for spontaneous, clinical speech using data augmentation

TL;DR

This paper presents a data augmentation approach to improve part-of-speech tagging accuracy on spontaneous clinical speech without relying on in-domain treebanks, by adapting out-of-domain newswire data.

Contribution

It introduces a novel data augmentation method to enhance POS tagging in clinical speech, bypassing the need for in-domain training data.

Findings

Augmented training data improves POS tagging accuracy on clinical speech.

The method outperforms baseline models trained without augmentation.

Effective for speech from patients with neurodegenerative conditions.

Abstract

This paper addresses the problem of improving POS tagging of transcripts of speech from clinical populations. In contrast to prior work on parsing and POS tagging of transcribed speech, we do not make use of an in domain treebank for training. Instead, we train on an out of domain treebank of newswire using data augmentation techniques to make these structures resemble natural, spontaneous speech. We trained a parser with and without the augmented data and tested its performance using manually validated POS tags in clinical speech produced by patients with various types of neurodegenerative conditions.