Continuous Learning from Human Post-Edits for Neural Machine Translation

MT Group at FBK Follow

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

11 Jun

3️⃣ "Cross-Attention is Half Explanation in Speech-to-Text Models"
👥 @sarapapi, @DennisFucci, @mgaido91, @negri_teo, @luisabentivogli
🇪🇺 DVPS EU project
📄

Reply on Twitter 2065078601976856833 Retweet on Twitter 2065078601976856833 2 Like on Twitter 2065078601976856833 2 Twitter 2065078601976856833

Avatar MT Group at FBK @fbk_mt ·

11 Jun

1️⃣ "Do What I Say: A Spoken Prompt Dataset for Instruction-Following"
👥 @MaikeZufle, @sarapapi, Fabian Retkowski, Szymon Mazurek, @mkasztelnik, Alexander Waibel, @luisabentivogli, @_janius_
🇪🇺 Meetween EU project
📄

Reply on Twitter 2065078592405410025 Retweet on Twitter 2065078592405410025 3 Like on Twitter 2065078592405410025 2 Twitter 2065078592405410025

Avatar MT Group at FBK @fbk_mt ·

11 Jun

We're excited to share that three papers from our lab have been accepted at #Interspeech2026 !! 🍾

#SpeechTranslation #SpeechAI #NLProc #FBK #Interspeech

Reply on Twitter 2065078587946889435 Retweet on Twitter 2065078587946889435 6 Like on Twitter 2065078587946889435 8 Twitter 2065078587946889435

Avatar MT Group at FBK @fbk_mt ·

10 Jun

Our pick of the week by
@lina_conti

: "Greater accessibility can amplify discrimination in generative AI" by
@CarolinHolterm, @minhducbui_nlp, @KaitlynZhou, @vjhofmann, @kelina1124, @anne_lauscher
📰
#GenderBias #SpeechLLM

Lina Conti @lina_conti

Pick of the week @fbk_mt: "Greater accessibility can amplify discrimination in generative AI"

Gender bias in speech-based LLMs examined from multiple angles: a user survey, automatic bias measurement, and pitch manipulation experiments.

https://arxiv.org/pdf/2603.22260

Reply on Twitter 2064764921062056414 Retweet on Twitter 2064764921062056414 3 Like on Twitter 2064764921062056414 6 Twitter 2064764921062056414