19015153. Techniques and Models for Multilingual Text Rewriting (GOOGLE LLC)
Techniques and Models for Multilingual Text Rewriting
Organization Name
Inventor(s)
Xavier Eduardo Garcia of New York NY US
Noah Constant of Cupertino CA US
Xiaoyue Guo of San Francisco CA US
Parker Riley of Mountain View CA US
Techniques and Models for Multilingual Text Rewriting
This abstract first appeared for US patent application 19015153 titled 'Techniques and Models for Multilingual Text Rewriting
Original Abstract Submitted
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.
(Ad) Transform your business with AI in minutes, not months
Trusted by 1,000+ companies worldwide
