English

Detecting dementia in Mandarin Chinese using transfer learning from a parallel corpus

Computation and Language 2019-06-04 v2

Abstract

Machine learning has shown promise for automatic detection of Alzheimer's disease (AD) through speech; however, efforts are hampered by a scarcity of data, especially in languages other than English. We propose a method to learn a correspondence between independently engineered lexicosyntactic features in two languages, using a large parallel corpus of out-of-domain movie dialogue data. We apply it to dementia detection in Mandarin Chinese, and demonstrate that our method outperforms both unilingual and machine translation-based baselines. This appears to be the first study that transfers feature domains in detecting cognitive decline.

Keywords

Cite

@article{arxiv.1903.00933,
  title  = {Detecting dementia in Mandarin Chinese using transfer learning from a parallel corpus},
  author = {Bai Li and Yi-Te Hsu and Frank Rudzicz},
  journal= {arXiv preprint arXiv:1903.00933},
  year   = {2019}
}

Comments

NAACL 2019 (Short paper)

R2 v1 2026-06-23T07:56:47.646Z