LAC (Language Asset Creator ) solution released by Kawamura International

Kawamura International has recently released its new LAC (Language Asset Creator ) solution. With LAC, users can create custom training data sets which can be used to train custom machine translation (MT) engines. LAC is available as part of XMAT, a machine assisted translation platform provided by Kawamura International, which offers different MT solutions, including Globalese. By combining the services from LAC, XMAT and Globalese, users can benefit from custom neural MT engines even if they have only a limited amount of own training data.

Important information regarding the CVE-2021-44228 bug

We can confirm that we are not using the Log4j Java code library in our self-developed Globalese code, services, and environment.

We are checking continuously if there is any impact from 3rd party products/services. We are following the events around the CVE-2021-44228 bug, and will take measurements if any new solution, patch, or fix will be available.

Partnership with t’works

Globalese MT is very happy to welcome t’works in the Globalese user community. t’works is a one stop translation service provider specialising in highly individual, complex projects and is based in 13 locations across 6 European countries. Globalese is excited to work with t’works and to help offer t’works’ clients the increased productivity benefits that machine translation brings. We’re looking forward to building a long and successful relationship.

Data Center Maintenance

Update: all Globalese systems are up and running. Thank you for your patience! IMPORTANT: on 26th July 2019, between 17:00 and 24:00 CEST, the Globalese systems will not be available due to planned Data Center Maintenance. Any updates will be posted in this news.

Report on custom NMT from Intento

Intento have released a very interesting report comparing different providers of custom Neural MT solutions. We are proud to see Globalese doing well based on automated evaluation metrics. The position Globalese achieved in human evaluation is mainly determined by the relatively higher number of inaccuracies with numbers and figures, which we have worked on to improve in version 3.5. Considering the fact that one of Globalese's strengths is handling tags, we believe that Globalese, as a 100% neural, 100% custom system, gives a real competitive advantage to our users.