Extending OpenNMTs TensorFlow Lite to Include Transformer Models

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2021
Accession Number
AD1144269

Entities

People

  • Gerardo Cervantes
  • Stephen Larocca

Organizations

  • United States Army Research Laboratory

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Central Processing Units
  • Computational Science
  • Computer Languages
  • Decoding
  • Dynamic Range
  • Information Science
  • Instructions
  • Language
  • Machine Learning
  • Machine Translation
  • Military Research
  • Natural Language Processing
  • Neural Networks
  • Recurrent Neural Networks
  • Translations
  • Vocabulary

Readers

  • Database Systems and Applications
  • Military Logistics and Supply Chain Management
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Space