Charles Explorer logo
🇬🇧

MTMonkey: A Scalable Infrastructure for a Machine Translation Web Service

Publication at Faculty of Mathematics and Physics |
2013

Abstract

We present a web service which handles and distributes JSON-encoded HTTP requests for machine translation (MT) among multiple machines running an MT system, including text pre- and post processing. It is currently used to provide MT between several languages for cross-lingual information retrieval in the Khresmoi project.

The software consists of an application server and remote workers which handle text processing and communicate translation requests to MT systems. The communication between the application server and the workers is based on the XML-RPC protocol.

We present the overall design of the software and test results which document speed and scalability of our solution. Our software is licensed under the Apache 2.0 licence and is available for download from the Lindat-Clarin repository and Github.