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

04/04/2019
by   Tasnim Mohiuddin, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/20/2019

Weakly-Supervised Concept-based Adversarial Learning for Cross-lingual Word Embeddings

Distributed representations of words which map each word to a continuous...
research
05/26/2023

On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss

Although unsupervised neural machine translation (UNMT) has achieved suc...
research
09/23/2020

Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages

Unsupervised translation has reached impressive performance on resource-...
research
01/18/2018

An Iterative Closest Point Method for Unsupervised Word Translation

Unsupervised word translation from non-parallel inter-lingual corpora ha...
research
06/27/2019

Latent Optimization for Non-adversarial Representation Disentanglement

Disentanglement between pose and content is a key task for artificial in...
research
03/11/2020

Visual Grounding in Video for Unsupervised Word Translation

There are thousands of actively spoken languages on Earth, but a single ...
research
07/01/2018

Augmented Cyclic Adversarial Learning for Domain Adaptation

Training a model to perform a task typically requires a large amount of ...

Please sign up or login with your details

Forgot password? Click here to reset