For a longer list of our text and speech translation projects and datasets, scroll down.
Machine Translation Research Group
-
ELITR - Simultaneous speech translation
-
elitr.eu: The project “ELITR, European Live Translator” supported by the EU under the Horizon 2020 programme and coordinated by Ondřej Bojar, created and provides a system for automatic transcription and simultaneous translation for live events, e.g. conference presentations; ready to complement or sometimes even substitute simultaneous interpreting. ELITR also explored the topic of automatic minuting, i.e. speech summarization.
-
CHARLES TRANSLATOR (2019-)
-
Neural machine translation between Ukrainian and Czech. Project page: https://ufal.mff.cuni.cz/ufal-ukraine. Freely available at Charles Translator for Ukraine and as an app for Android.
-
CUBITT (2020-)
-
Our neural machine translation system matched humans in translation quality already in 2020, two years before ChatGPT made the Transformer architecture popular. Martin Popel's team results featured in Nature Communications. The system can be freely tested at https://lindat.cz/cubbitt.
-
Chimera (2013-2015)
-
Chimera, a hybrid Machine Translation system which was developed at the Institute of Formal and Applied Linguistics, combines a deep-syntactic transfer-based system TectoMT, very large parallel and monolingual data in a Moses factored setup to ensure morphological coherence, and finally Depfix, a rule-based automatic post-editing system that corrects grammaticality (agreement and valency) of the output as well as some features vital for adequacy, namely lost negation. The system was able to succesfully compete the best machine translation systems tech.ihned.cz/hnfuture/... [learn more].
Other MT Projects