Last chance to join this three-day virtual gathering for Machine Translation researchers, developers, students and users! https://unbabel.com/event-mt-half-marathon/
Category: News
User-Focused Marian will take part in WMT2021 Efficiency Shared Task. Check out the task description and join here! ☜(ﾟヮﾟ☜)
Code and documentation on how to do forced translation with Marian is now available! This functionality aims to support users in improving translation quality by injecting translations from their own bilingual terminology dictionaries. To expand coverage and support morphologically rich languages, it also supports inflecting entries in the bilingual terminology dictionary. A full description of …
Marian has new user documentation! This new documentation covers the expression graph and its operators, and describes how they’re used to perform computation in Marian – as well as how you can build your own graphs and operators. See more here.
On the 3rd of December User-Focused Marian took part in META-FORUM international conference series. Check out our poster here!
Code and documentation on Marian usage with factors have been published. With this improvement user now is able to train a model with source and/or target-side factors. Factors carry side information about a token in the sentence, which can be used for a variety of purposes including implementing forced translation. In neural machine translation, factors …
Project results – Implementation of Factored TranslationRead More »
The website of the User focused Marian project was launched on 20 April 2020. In its first version, this website provides a basic overview of the project, activities it plans to run and planned releases. In the future it is also planned to publish regular report on the project progress and events. To stay updated come …
We are pleased to announce that the CEF Telecom Project User Focused Marian has been officially launched with a successful kick-off meeting. The University of Edinburgh, Unbabel and Tilde will work towards improving the open-source Marian neural automated translation toolkit. Marian is already widely used in production by eTranslation, Microsoft Translator, World Intellectual Property Organization, …