Software

SubSONAR

by | May 17, 2024 | | 0

SubSONAR evaluates the quality of SRT files using the multilingual multimodal SONAR model. The evaluation accounts for the semantic similarity (computed as a cosine similarity) between each subtitle block and the corresponding...

Read More

AQET

by | May 30, 2023 | | 0

AQET (Adaptive Quality Estimation Tool) is an open-source package for performing Quality Estimation for Machine Translation able to continuously learn from post-edited sentences.

Read More

IRSTLM

by | May 30, 2023 | | 0

The IRST Language Modeling (IRSTLM) Toolkit features algorithms and data structures suitable to estimate, store, and access very large n-gram language models.

Read More

MOSES

by | May 30, 2023 | | 0

Moses is a statistical machine translation system that allows you to automatically train translation models for any language pair.

Read More
Loading

MT Group at FBK Follow

#MachineTranslation Research Unit @FBK_research. #nlproc #deeplearning #ai

Avatar
Retweet on Twitter MT Group at FBK Retweeted
Avatar Meetween @meetweeneu ·
19 Mar

🎙️ Two people. Two languages. One conversation! 
No delays. No switching languages. No one is left out.

This is what we are building.

#SpeechAI #MultilingualAI #HorizonEurope

Reply on Twitter 2034649968183517549 Retweet on Twitter 2034649968183517549 1 Like on Twitter 2034649968183517549 3 Twitter 2034649968183517549
Avatar MT Group at FBK @fbk_mt ·
18 Mar

🎉 We’re very happy to welcome our new postdoc @LucaCorbucci , who will be working on multimodal LLMs.
Looking forward to the exciting research ahead! 🚀

@FBK_research

Reply on Twitter 2034316123735232727 Retweet on Twitter 2034316123735232727 6 Like on Twitter 2034316123735232727 11 Twitter 2034316123735232727
Retweet on Twitter MT Group at FBK Retweeted
Avatar Eduardo Sánchez @eduardosg_ai ·
17 Mar

Four years ago, NLLB set a milestone with MT for 200 languages. Today we present OMT: a family of models that extend support to 1600 languages while delivering competitive results in high/mid-resource language, with our 1B-8B models matching frontier and open 70B LLMs.

🧵(1/n)

Reply on Twitter 2033978351967256809 Retweet on Twitter 2033978351967256809 9 Like on Twitter 2033978351967256809 29 Twitter 2033978351967256809
Retweet on Twitter MT Group at FBK Retweeted
Avatar İlker Kesen @ilker_kesen ·
17 Mar

📢I'm organizing a BoF session at #EACL2026 called Tokenization & Beyond, aiming to gather researchers exploring tokenization and alternatives such as byte-level and pixel-based approaches. Sign up using the form if you're interested! #NLProc @eaclmeeting

Reply on Twitter 2033932511332515935 Retweet on Twitter 2033932511332515935 13 Like on Twitter 2033932511332515935 44 Twitter 2033932511332515935
Load More