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

Revisiting Adversarial Autoencoder for Unsupervised Word Translation with Cycle Consistency and Improved Training

2019-04-04
Tasnim Mohiuddin, Shafiq Joty

Abstract

Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial methods in more challenging language pairs. In this work, we revisit adversarial autoencoder for unsupervised word translation and propose two novel extensions to it that yield more stable training and improved results. Our method includes regularization terms to enforce cycle consistency and input reconstruction, and puts the target encoders as an adversary against the corresponding discriminator. Extensive experimentations with European, non-European and low-resource languages show that our method is more robust and achieves better performance than recently proposed adversarial and non-adversarial approaches.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.04116

PDF

http://arxiv.org/pdf/1904.04116


Comments

Content