acm-header
Sign In

Communications of the ACM

ACM TechNews

Open Source Challenger Takes on Google Translate


Artist's depiction of automated language translation.

A new machine translation framework developed by researchers at Harvard University and the company Systran could serve as an alternative to services such as Google Translate.

Credit: CSO Staff

A new open source machine translation framework could serve as an alternative to closed-source projects such as Google Translate.

Open Source Neural Machine Translation (OpenNMT) is built on the work of researchers from Harvard University and machine-language software creator Systran. OpenNMT runs on the Torch scientific computing framework and uses the Lua language to interface with Torch.

The new open source neural network system for performing language translations works like other products in its class. The training process for OpenNMT models can be accelerated on any graphics-processing-unit-equipped system, but it can still take a long time--sometimes many weeks. The training process can be snapshotted and resumed on demand if needed.

For common language pairs such as English/French, the translations are very accurate, but OpenNMT does not supply pretrained language model data, which will limit its usefulness out of the box.

A live demo provided by Systran claims to use OpenNMT in conjunction with Systran's own work.

From InfoWorld
View Full Article

 

Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account