The consortium studies, designs, and implements innovative methodologies for KM based on the use of IE. From the scientific point of view, we focus on two aspects that are symmetric: how the use in KM poses requirements and challenges to IE and how the use of IE changes KM. From the practical point of view, we define tools and methodologies for IE-based KM.
Our pick of the week by @apierg: "Glitter: A Multi-Sentence, Multi-Reference #Benchmark for #Gender-Fair German Machine Translation" by A Pranav, Janiça Hackenbuchner, @peppeatta, @manuellardelli, @anne_lauscher (Findings #EMNLP2025)
#MT #Translation
Impressive work by the Glitter team: a new human-made benchmark for German gender-inclusive MT with long passages and multiple inclusive approaches + experiments showing that MT systems and LLMs still fall short in generating inclusive outputs.
https://aclanthology.org/2025.findings-emnlp.1002/ ✨
@fbk_mt
Our pick of the week by @dhairya_su47605: "How Does #Quantization Affect #Multilingual #LLMs?" by @cheeesio, @TheyCallMeMr_, Hongyu Chen, @d_aumiller, @ahmetustun89, @sarahookr, @seb_ruder (Findings EMNLP, 2024)
Pick of the week @fbk_mt: How Does Quantization Affect Multilingual LLMs?
Quantization has become a widely adopted technique for model compression. This work investigates the impact of quantization on different languages in multilingual LLMs.
https://aclanthology.org/2024.findings-emnlp.935.pdf
🗣️ Calling all researchers & practitioners in #Speech #Translation!
Help shape the future of the #Simultaneous track at @iwslt 2026. Your input matters!
Please spare 3-5 min to fill out this quick survey📋:
➡️
🚀 JOB ALERT 3: The FBK's MT Unit is hiring!
Join us as a Researcher in Responsible & Trustworthy NLP and advance ethical, fair, and transparent language technologies. If you care about building safe and accountable AI systems, you can apply here:
👉 https://jobs.fbk.eu/Annunci/Offerte_di_lavoro_A_Researcher_in_Responsible_and_Trustworthy_NLP_241757983.htm