Unsupervised Learning and Representation of Mandarin Tonal Categories by a Generative CNN
This addresses the challenge of modeling human language acquisition of complex tonal patterns without labeled data, though it is incremental in applying existing methods to a specific linguistic domain.
The paper tackled the problem of unsupervised learning of Mandarin Chinese tonal categories using a generative CNN model (ciwGAN), achieving statistically significant differences in F0 across categorical variables, with the model trained on male tokens consistently encoding tone.
This paper outlines the methodology for modeling tonal learning in fully unsupervised models of human language acquisition. Tonal patterns are among the computationally most complex learning objectives in language. We argue that a realistic generative model of human language (ciwGAN) can learn to associate its categorical variables with Mandarin Chinese tonal categories without any labeled data. All three trained models showed statistically significant differences in F0 across categorical variables. The model trained solely on male tokens consistently encoded tone. Our results sug- gest that not only does the model learn Mandarin tonal contrasts, but it learns a system that corresponds to a stage of acquisition in human language learners. We also outline methodology for tracing tonal representations in internal convolutional layers, which shows that linguistic tools can contribute to interpretability of deep learning and can ultimately be used in neural experiments.