Amazon Technologies, Inc.

Aakash Upadhyay

Georgiana Dinu

Eric J Nowell

Prashant Mathur

Rama Krishna Sandeep Pokkunuri

Xianglong Huang

Yaser Al-Onaizan

Jian Wang

Marcello Federico

Maria Nadejde

Anna Currey

Margo Helena Lynch

Shuoren Fu

Tatyana Badeka

Jenyuan Wang

William Jew Wong

Dengke Liu

Advait Bhatwadekar

Haiyu Yao

Prajwal Gadad

A respective label set is obtained for a number of translation unit pairs, with each pair comprising a set of language elements in a first language and the translation of the set of language elements to a second language. The label set includes values of one or more translation customization attributes. A value of such an attribute associated with a translation request is identified. A translated version of an input set of language elements indicated in the translation request is generated in accordance with the value of the attribute, using a machine learning model trained with the help of the label sets.

Customized machine translation using client-specified attributes

Machine learning translation models may be selectively tuned to provide custom machine translations. A request to translate input text from an input language to a target language may be received. A tuning data set for translating the input text to the target language may be identified and searched to select pairs of texts in the tuning data according to comparisons with the input text. A machine learning model used to translate into the target language may be tuned using only second texts in the target language in the selected pairs of texts. The tuned machine learning model may then be used to translate the input text into the target language.

Selectively tuning machine translation models for custom machine translations

A translation system receives examples of translations between a first language and a second language. In response to receiving request to translate a source text from the first language to the second language, the system ranks the examples based on the example's applicability to one or more portions of the source text. The system performs additional training of a neural network that was pre-trained to translate from the first language to the second language, where the additional training is based on one or more top-ranking examples. The system translates the source text to the second language using the additionally trained neural network.

Machine translation with adapted neural networks

Growing community of inventors

Seattle, WA, United States of America

Aakash Upadhyay