Exploring How Generative Adversarial Networks Learn Phonological Representations

by   Jingyi Chen, et al.
The Ohio State University

This paper explores how Generative Adversarial Networks (GANs) learn representations of phonological phenomena. We analyze how GANs encode contrastive and non-contrastive nasality in French and English vowels by applying the ciwGAN architecture (Begus 2021a). Begus claims that ciwGAN encodes linguistically meaningful representations with categorical variables in its latent space and manipulating the latent variables shows an almost one to one corresponding control of the phonological features in ciwGAN's generated outputs. However, our results show an interactive effect of latent variables on the features in the generated outputs, which suggests the learned representations in neural networks are different from the phonological representations proposed by linguists. On the other hand, ciwGAN is able to distinguish contrastive and noncontrastive features in English and French by encoding them differently. Comparing the performance of GANs learning from different languages results in a better understanding of what language specific features contribute to developing language specific phonological representations. We also discuss the role of training data frequencies in phonological feature learning.


page 6

page 8


ClusterGAN : Latent Space Clustering in Generative Adversarial Networks

Generative Adversarial networks (GANs) have obtained remarkable success ...

Contrastive Disentanglement in Generative Adversarial Networks

Disentanglement is defined as the problem of learninga representation th...

Adversarial Feature Learning

The ability of the Generative Adversarial Networks (GANs) framework to l...

Impedance-based Capacity Estimation for Lithium-Ion Batteries Using Generative Adversarial Network

This paper proposes a fully unsupervised methodology for the reliable ex...

Learning Non-deterministic Representations with Energy-based Ensembles

The goal of a generative model is to capture the distribution underlying...

Handwriting Profiling using Generative Adversarial Networks

Handwriting is a skill learned by humans from a very early age. The abil...

Please sign up or login with your details

Forgot password? Click here to reset