PUBLICATIONS
On the successful language model training for one of our clients
We’re happy to share a recent excellent example of engine customization with you: the preparation of a machine translation language model for one of our key clients. During preparation for the training, we gathered a large high-quality translation base for this client, which undoubtedly played a significant role during the training process.
The evaluation of the post-training test translation has shown that the engine handled the translation of the client’s marketing materials 10% better than other popular stock engines (based on hLEPOR metrics that determine the number of identically translated segments in the machine and the reference (translated by a human and well-edited) translations):
- Google – 51 %
- Amazon – 51 %
- ModernMT – 49 %
- Trained ModernMT model – 60 %
Such metrics results for the trained model are truly successful in the marketing domain due to its complexity and creativeness.
We’re happy to note that many production departments of Janus Worldwide have been working with our MT team R&D for quite a while now, which helps us earn the trust of our clients who have just started their journey into the machine translation area. Every new client earned is a big victory over prejudice for us. These victories grow in value each time we manage to train a language model from scratch and get machine translation of great quality.
Machine Translation Specialist
Irina Shakhmetova
In 2014, I graduated from the Pyatigorsk State Linguistic University with a master degree in Cognitive Linguistics. Since 2015, I worked at a linguistics company as a Machine Translation Specialist and a Post Editor. In 2024, I started working at Janus Worldwide in the R&D department, and handle issues related to training and selection of engines, evaluate the machine translation quality, perform analysis, and participate in development and testing of the linguistic software.
