**** We apologize for the multiple copies of this email. In case you are already registered to the next webinar, you do not need to register again. ****
Dear colleague,
We are happy to announce the next webinar in the Language Technology webinar series organized by the HiTZ Chair of AI< (https://hitz.eus). You can view the videos of previous webinars and the schedule for upcoming webinars here: http://www.hitz.eus/webinars
Next webinar:
Speaker: André F. T. Martins (Universidade de
Lisboa)
Title: xCOMET, Tower, EuroLLM: Open &
Multilingual LLMs for Europe
Date: Thursday, May 8, 2025 - 15:00 CET
Summary: Today, LLMs are Swiss knives and MT one of
their tools. Is this the end of MT research? In this talk, I
argue that the connection between LLM and MT research is
two-way. I present some of our recent work advancing
multilingual LLMs, tools to estimate their quality, and how
the two can be combined for test-time scaling. First, I
present xCOMET, an open-source learned metric which
integrates sentence-level evaluation and error span
detection, exhibiting state-of-the-art performance across
all types of meta-evaluation (sentence-level, system-level,
and error span detection). Moreover, it does so while
highlighting and categorizing error spans, thus enriching
the quality assessment. Then, I present Tower, a suite of
open multilingual LLMs for translation-related tasks. Tower
models are created through continued pretraining on a
carefully curated multilingual mixture of monolingual and
parallel data. The combination of Tower with COMET reranking
obtained the best results in 8 out of 11 language pairs in
the WMT General Translation shared task, according to human
evaluation. Finally, I describe EuroLLM, an ongoing EU-made
project whose goal is to train an open multilingual LLM from
scratch using the European HPC infrastructure (EuroHPC). The
last release (EuroLLM-9B) supports 35 languages, including
all 24 official EU languages, and it achieves strong results
in various benchmarks, comparable or better than the best
existing models of similar size.
xCOMET: https://huggingface.co/collections/Unbabel/xcomet-659eca973b3be2ae4ac023bb
Tower: https://huggingface.co/collections/Unbabel/tower-659eaedfe36e6dd29eb1805c
EuroLLM: https://huggingface.co/blog/eurollm-team/eurollm-9b
Bio: André F. T. Martins (PhD 2012, Carnegie Mellon
University and Instituto Superior Técnico; https://andre-martins.github.io/)
is an Associate Professor at Instituto Superior Técnico,
University of Lisbon, researcher at Instituto de
Telecomunicações, and the VP of AI Research at Unbabel. His
research, funded by a ERC Starting Grant (DeepSPIN) and
Consolidator Grant (DECOLLAGE), among other grants, include
machine translation, quality estimation, structure and
interpretability in deep learning systems for NLP. His work
has received several paper awards at ACL conferences. He
co-founded and co-organizes the Lisbon Machine Learning
School (LxMLS), and he is a Fellow of the ELLIS society and
co-director of the ELLIS Program in Natural Language
Processing. He is a member of the R&I advisory group of
EuroHPC, the European infrastructure for supercomputing.
Upcoming webinars:
· Mirella Lapata (Thursday, June 5, 2025)
If you are interested in participating, please complete this registration form: http://www.hitz.eus/webinar_izenematea
If you cannot attend this seminar, but you want to be informed of the following HiTZ webinars, please complete this registration form instead: http://www.hitz.eus/webinar_info
Best wishes,
HiTZ Zentroa
P.S: HiTZ will not grant any type of certificate for attendance at these webinars.