We need someone who has worked with this translator and can set up a translator from scratch in several languages or at least one language.
The translator needs to be trained for our subject - pharmaceuticals.
Languages-German, French, Spanish, Russian, Portuguese.
Hi Ludmila!
I think it would be great if you add a couple of details:
I would like also to highlight one important point here. OpenNMT is self-hosted. In other words, this “person” must be also able to build an API, setup it on a server, and help you integrate it into your workflow. I am sure you are already aware of this.
Kind regards,
Yasmin
Hello!
All texts are now in English. We need a translation from English to Spanish, German and 4 other languages. According to the API, we have a developer. We are looking for a person who will teach the program and help with the implementation of the program. I don’t understand the question: * Do you have datasets in pharmaceuticals for these languages? If so, how many sentences? Please specify.
Best Regards,
Ludmila
Dear Ludmila,
Many people use OPUS bilingual datasets/corpora to train generic MT systems. To train specialized MT systems, you need to have in-domain sentences; in your case in pharmaceuticals. Using these specialized translated sentences, you will train (or fine-tune) an MT system to be able to translate new pharmaceuticals sentences in the future.
Medical datasets are not so popular (let alone pharmaceuticals). Plus, even if you used a publicly available dataset to train a pharmaceutical MT system, the quality is not guaranteed. What companies usually do is that they use human translators to translate their own texts for some time, and then use these translated texts to train an MT system. If you already have internal translations of your own previous documents, that what my question was about.
I hope this is clear.
Kind regards,
Yasmin
Hello Ludmila,
Write me to alexeir@lingvanex.com and I will help you to setup translator based on OpenNMT
Regards,
Aliaksei