papers AI Learner
The Github is limit! Click to go to the new site.

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

2019-03-03
Bai Li, Yi-Te Hsu, Frank Rudzicz

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.00933

PDF

http://arxiv.org/pdf/1903.00933


Similar Posts

Comments