The Center for Responsible AI is one of the largest centers dedicated to Responsible AI, bringing together ten startups, eight research centers, a law firm, and five industry leaders, that will collaborate to develop 21 innovative AI products leveraged by Responsible AI technologies such as equity, explainability, and sustainability. The center is co-funded by the Portuguese PRR.

UTTER – Unified Transcription and Translation for Extended Reality – is a collaborative Research and Innovation project funded under Horizon Europe that aims to leverage large language models to build the next generation of multimodal eXtended reality (XR) technologies for transcription, translation, summarisation, and minuting. UTTER’s use-case prototypes will cover (i) a personal assistant for meetings that can improve communication in the online world and (ii) an advanced customer service assistant to support global markets.

QUARTZ (kwaliteitsbewuste automatische vertaling) is een baanbrekend onderzoeksproject gefinancierd door de ELISE Open Call om Responsible MT te bouwen voor conversatiegegevens: MT van hoge kwaliteit om nieuwe markten te ontsluiten waar kritische MT-fouten niet getolereerd kunnen worden.

MAIA maakt gebruik van geavanceerde technologieën voor machinaal leren en natuurlijke taalverwerking om meertalige AI-agentassistenten te bouwen en taalbarrières te elimineren. MAIA's 'vertaallaag' zal menselijke agenten in staat stellen klantondersteuning te bieden in realtime en in elke taal, met menselijke kwaliteit.

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). Terminology, on-the-fly domain adaptation, better documentation and GPU optimization are the focus areas in this Marian iteration.

Aims at building data for under-resourced languages in fields of public interest, such as Health and Justice. It’ll 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).

We’re working on advancing European language engines for borderless business communication. Create Europe’s Translation Layer, specifically, by enabling seamless human-quality translation between any pairing of the 24 official languages of the EU in different content types such as Email, Chat and Listings (P2020 Co-Funded Project).

Setting up a quality gate and crowdsourcing workflow to improve translation quality in specific domains. 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).

Tijdige en accurate communicatie is essentieel voor crisisbeheer, maar wat als de enige beschikbare informatie in een taal is die u niet spreekt? INTERACT is een interdisciplinair Europees project dat is opgezet om tegemoet te komen aan de behoefte aan kwaliteitsvertaling in gezondheidscrisisscenario's.

Transcription can be a big piece of translation flows, especially when it comes to audiovisual content. This project aims to research & develop a technical solution for automatic transcription and translation of audiovisual content by leveraging a community of human translators (P2020 Co-Funded Project).

Deep learning zorgt voor een revolutie op het gebied van Natural Language Processing (NLP), met doorbraken in automatische vertaling, spraakherkenning en het beantwoorden van vragen. Nieuwe taalinterfaces (digitale assistenten, messenger apps, customer service bots) zijn in opkomst als de volgende technologieën voor naadloze, meertalige communicatie tussen mensen en machines.

Unbabel’s Internationalization Plan (“Unbabel 2017-2019: Plano de Internacionalização”) is a project led by Unbabel and co-funded by Portugal 2020 – Sistema de Incentivos à Internacionalização das PME.

“Unbabel 2017: A new ecosystem of Machine + Crowd Translation” is a project led by Unbabel and co-funded by Portugal 2020 – Sistema de Incentivos à Investigação e Desenvolvimento Tecnológico (SI I&DT)

Meer informatie
Paper

XCOMET is a cutting-edge, open-source metric designed to be more interpretable and better aligned with MQM human evaluations. XCOMET combines sentence-level evaluation, similar to neural metrics such as COMET and BLEURT, and error span detection capabilities.

Meer informatie

TowerLLM is a suite of multilingual large language models (LLM) optimized for translation-related tasks ranging from pre-translation, to translation and evaluation tasks, such as machine translation (MT), automatic post-editing (APE), and translation ranking. Tower is built on top of LLaMA2 [1], comes in two sizes — 7B and 13B parameters —, and currently supports 10 languages.

Meer informatie

CometKiwiXL is large language model (LLM) specialized in predicting the quality of a translation. CometKiwi XL (3.5B) and CometKiwi XXL (10.7B) are the open-sourced versions of our state-of-the-art Quality Estimation model.

Meer informatie

MT-Telescope biedt een fijnmazige, visuele vergelijking van de kwaliteitsprestaties van twee automatische vertaling (MT)-systemen. De automatische kwaliteitsscore wordt verbeterd, zodat gebruikers de kwaliteitsprestaties kunnen filteren op trefwoorden, terminologie en segmentlengte. MT-Telescope is beschikbaar als open-source ten behoeve van de bredere MT R&D-gemeenschap.

COMET (Crosslingual Optimized Metric for Evaluation of Translation) is een nieuw neuraal kader voor het trainen van evaluatiemodellen voor meertalige automatische vertaling (MT). COMET voorspelt menselijke beoordelingen van MT-kwaliteit. Dit 'gebruiksklare' getrainde COMET-model is als open-source beschikbaar ten behoeve van de bredere MT R&D-gemeenschap.

Quality estimation (QE) is one of the challenges in MT: it evaluates a 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. The accompanying paper won the best system paper at ACL 2019.