Accession Number:

AD1144269

Title:

Extending OpenNMTs TensorFlow Lite to Include Transformer Models

Descriptive Note:

[Technical Report, Technical Note]

Corporate Author:

ARMY RESEARCH LAB

Personal Author(s):

Report Date:

2021-07-01

Pagination or Media Count:

19

Abstract:

Since its release in 2017 the OpenNMT project has provided open development tools for Neural Machine Translation NMT including machine-learning inference with artificial neural-network models on Android platforms. Rapid advances in OpenNMT methods were achieved using TensorFlow since 2018 however, most of these advances were not deployable for use on Android platforms pending completion of the TensorFlow Lite library. The US Army Combat Capabilities Development Command Army Research Laboratorys Shareable Components project team closely tracked progress on TensorFlow Lite and succeeded in implementing a new method for converting OpenNMT models from standard TensorFlow to the Lite variant. Deployable on Android devices, these converted models provide important gains in execution speed while occupying less space. This extension adds more features to OpenNMT-tf, which allows the export of better-performing Transformer models onto Android. Beam search and unk replacement have also been added to this extension, which will generally help increase the performance.

Descriptors:

Subject Categories:

Distribution Statement:

[A, Approved For Public Release]