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

Federated Learning Of Out-Of-Vocabulary Words

2019-03-26
Mingqing Chen, Rajiv Mathews, Tom Ouyang, Françoise Beaufays

Abstract

We demonstrate that a character-level recurrent neural network is able to learn out-of-vocabulary (OOV) words under federated learning settings, for the purpose of expanding the vocabulary of a virtual keyboard for smartphones without exporting sensitive text to servers. High-frequency words can be sampled from the trained generative model by drawing from the joint posterior directly. We study the feasibility of the approach in two settings: (1) using simulated federated learning on a publicly available non-IID per-user dataset from a popular social networking website, (2) using federated learning on data hosted on user mobile devices. The model achieves good recall and precision compared to ground-truth OOV words in setting (1). With (2) we demonstrate the practicality of this approach by showing that we can learn meaningful OOV words with good character-level prediction accuracy and cross entropy loss.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.10635

PDF

http://arxiv.org/pdf/1903.10635


Comments

Content