Research at Unbabel
Where machine learning meets human ingenuity
Our research team is advancing the state of the art — and changing the way humans work for the better.
Leading voices in the field
At Unbabel, we’ve built up a team of area experts from around the world, with particular strengths in natural language processing.
Recent publications
We support our researchers as they place their innovative work in top publications. You can see some recent highlights from our team below.
- 2019
Projects
All our research is designed for maximum impact. For our contributions to natural language processing and applied AI, we’ve received numerous awards.
User-Focused Marian
Improve the pre-existing neural machine translation toolkit “Marian” to address the needs of CEF eTranslation and to broaden its user base (H2020 Co-Funded Project).
MT4ALL
Contribute to the CEF Automated Translation Building block by enlarging its coverage for language pairs and domains for which parallel data does not exist (H2020 Co-Funded Project).
Unbabel4EU
Create Europe’s Translation Layer by enabling seamless human-quality translation between any pairing of the 24 official languages of the EU (P2020 Co-Funded Project).
OpenKiwi
Quality estimation (QE) is one of the missing pieces of machine translation: its goal is to evaluate a translation system’s quality without access to reference translations. We released OpenKiwi, a PyTorch-based open-source framework that implements the best QE systems from WMT 2015-18 shared tasks, making it easy to experiment with these models under the same framework. The accompanying paper won the best system paper at ACL 2019.
APE-QUEST
Boost CEF eTranslation with Automated Post-Editing (APE) & Quality Estimation (QE) for Electronic Exchange of Social Security Information (EESSI) and Online Dispute Resolution (ODR) DSIs and related national services (H2020 Co-Funded Project).
INTERACT - International Network On Crisis Translation
Timely and accurate communication is essential for crisis management, but what if the only information available to you is in a language you cannot understand?
Unbabel Scribe
Research & develop a solution for automatic transcription and translation of audiovisual content combined with a community of human translators (P2020 Co-Funded Project).
DeepSPIN
Deep learning is revolutionizing the field of Natural Language Processing (NLP), with breakthroughs in machine translation, speech recognition, and question answering. New language interfaces (digital assistants, messenger apps, customer service bots) are emerging as the next technologies for seamless, multilingual communication among humans and machines.
Most Innovative Company
2017, 2015
Best Global Machine Translation Quality Estimation System
2019, 2016
Blending Human & Artificial Intelligence, in partnership with Concentrix, UK
2019
CBInsights AI List of Most Innovative Artificial Intelligence Startups for Disruptive Technology of the Year
2019
Want to do research with us?
Our AI team is growing — and we’re looking for candidates with unique skills and stories.