Google Inc.

Xavier Eduardo Garcia

Orhan Firat

Yonghui Wu

Andrew M Dai

Melvin Jose Johnson Premkumar

Slav Petrov

Yanping Huang

Yuanzhong Xu

Aurko Roy

Maxim Krikun

Nan Du

David Richard So

Rohan Anil

Noah Constant

Gaurav Mishra

Siamak Shakeri

Yong Cheng

Jonathan Hudson Clark

Erica Ann Moreira

Yujing Zhang

Zachary Alexander Nado

Kefan Xiao

Jin Young Sohn

Eric Jun Jie Ni

Vladimir Feinberg

Parker Riley

Xiaoyue Guo

Dmitry Lepikhin

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network to perform any one or more of a variety of machine learning tasks. For example, the neural network can be configured as a generative neural network, e.g., an autoregressive generative neural network.

Training of large neural networks

The technology provides a model-based approach for multilingual text rewriting that is applicable across many languages and across different styles including formality levels or other textual attributes. The model is configured to manipulate both language and textual attributes jointly. This approach supports zero-shot formality-sensitive translation, with no labeled data in the target language. An encoder-decoder architectural approach with attribute extraction is used to train rewriter models that can thus be used in 'universal' textual rewriting across many different languages. A cross-lingual learning signal can be incorporated into the training approach. Certain training processes do not employ any exemplars. This approach enables not just straight translation, but also the ability to create new sentences with different attributes.

Techniques and models for multilingual text rewriting

Growing community of inventors

New York, NY, United States of America

Xavier Eduardo Garcia