公开(公告)号：US20180107655A1

公开(公告)日：2018-04-19

申请号：US15295582

申请日：2016-10-17

Applicant: Google Inc.

Inventor： Melvin Jose Johnson Premkumar ,  Sarah Nguyen ,  Klaus Macherey

IPC: G06F17/28

CPC classification number: G06F17/289 ,  G06F17/2872

Abstract: A computer-implemented method can include obtaining, by a server computing device, a machine translation model relating sets of source words in a source language to sets of target words in a different target language, each of the sets of source words and target words being labeled with a level of formality with respect to its corresponding language. The method can include receiving, by the server computing device, a request to obtain a translated text representing a translation of a text from the source language to the target language, the request further specifying a desired level of formality for the translated text. The method can include in response to receiving the request, obtaining, by the server computing device, the translated text by translating the text using the machine translation model and the desired level of formality. The method can further include outputting, by the server computing device, the translated text.

公开(公告)号：US20180129972A1

公开(公告)日：2018-05-10

申请号：US15394708

申请日：2016-12-29

Applicant: Google Inc.

Inventor： Zhifeng Chen ,  Michael Schuster ,  Melvin Jose Johnson Premkumar ,  Yonghui Wu ,  Quoc V. Le ,  Maxim Krikun ,  Thorsten Brants

IPC: G06N99/00 ,  G06F17/28

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.