Lightnews — Scholar-powered news

Reposted

AILC-NLP @ailc-nlp.bsky.social · 12d

Thanks to all the participants! #clicit2025

5 11

Reposted

MT Group at FBK @fbk-mt.bsky.social · 13d

Our very own @sarapapi.bsky.social presenting FAMA at #clicit2025:

📗Paper: clic2025.unica.it/wp-content/u...
🔗 Models: hf.co/collections/...
📊 Data: hf.co/datasets/FBK...
💻 Code: github.com/hlt-mt/FBK-f...

Joint work with @speechtekfbk.bsky.social

2 4

Reposted

AILC-NLP @ailc-nlp.bsky.social · 14d

Last oral session of the first #clicit2025 day! See you all at the welcome drink!

1 2

sarapapi.bsky.social @sarapapi.bsky.social · 14d

I’m the guest 🙋🏻‍♀️

DH Group at FBK @dh-fbk.bsky.social · 15d

We are on our way to Casteddu for #clicit2025 with a guest from @fbk-mt.bsky.social @ailc-nlp.bsky.social

2

sarapapi.bsky.social @sarapapi.bsky.social · 14d

🚀 Excited to present FAMA, the first large-scale #OpenScience #Speech foundation model for 🇮🇹 Italian & 🇬🇧 English, at #clicit2025 (17:30–18:45 oral session)!

🔗 Models: hf.co/collections/...
📊 Data: hf.co/datasets/FBK...
💻 Code: github.com/hlt-mt/FBK-f...
📄 Preprint: arxiv.org/pdf/2505.22759

2 7

sarapapi.bsky.social @sarapapi.bsky.social · 20d

An interesting survey about #RAG and its interplay with #multimodality: Retrieval-Augmented Generation for AI-Generated Content: A Survey

arxiv.org/pdf/2402.19473

@fbk-mt.bsky.social

arxiv.org

Reposted

AI Research Updates | arXiv cs.AI @arxiv-cs-ai.bsky.social · Aug 4

MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
Read more: https://arxiv.org/html/2507.19634v1

1 1

Reposted

arxiv cs.CL @arxiv-cs-cl.bsky.social · Jul 29

Sara Papi, Maike Z\"ufle, Marco Gaido, Beatrice Savoldi, Danni Liu, Ioannis Douros, Luisa Bentivogli, Jan Niehues
MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
https://arxiv.org/abs/2507.19634

4 4

Reposted

MT Group at FBK @fbk-mt.bsky.social · Aug 2

@sarapapi.bsky.social presented her TACL paper: “How real is your real-time simultaneous speech-to-text translation system?”

👉 aclanthology.org/2025.tacl-1.14/
(2/6)

1 1 3

sarapapi.bsky.social @sarapapi.bsky.social · Jul 27

Official paper: direct.mit.edu/tacl/article...

How “Real” is Your Real-Time Simultaneous Speech-to-Text Translation System?

direct.mit.edu

1

sarapapi.bsky.social @sarapapi.bsky.social · Jul 27

🔥 Is your real-time SimulST system REAL?

Our TACL paper analyzes 110 works and reveals:
🚫 Overreliance on short-form speech
🌀 Terminology chaos
📉 Real-world deployment gaps
We bring order-New taxonomy, trends & recommendations!

📍#ACL2025 Poster: Monday 11-12:30, Hall 4/5

#Speech #SpeechTech

1 5

Reposted

Beatrice Savoldi @bsavoldi.bsky.social · Jun 3

🔍 Stiamo studiando come l'AI viene usata in Italia e per farlo abbiamo costruito un sondaggio!

👉 bit.ly/sondaggio_ai...

(è anonimo, richiede ~10 minuti, e se partecipi o lo fai girare ci aiuti un sacco🙏)

Ci interessa anche raggiungere persone che non si occupano e non sono esperte di AI!

Qualtrics Survey | Qualtrics Experience Management

The most powerful, simple and trusted way to gather experience data. Start your journey to experience management and try a free account today.

bit.ly

1 18 16

sarapapi.bsky.social @sarapapi.bsky.social · May 30

🚀 New tech report out! Meet FAMA, our open-science speech foundation model family for both ASR and ST in 🇬🇧 English and 🇮🇹 Italian.

The models are live and ready to try on @hf.co:
🔗 huggingface.co/collections/...

📄 Preprint: arxiv.org/abs/2505.22759

#ASR #ST #OpenScience #MultilingualAI

FAMA - a FBK-MT Collection

The First Large-Scale Open-Science Speech Foundation Model for English and Italian

huggingface.co

3 7

Reposted

Tiago Pimentel @tpimentel.bsky.social · May 29

If you're finishing your camera-ready for ACL or ICML and want to cite co-first authors more fairly, I just made a simple fix to do this! Just add $^*$ to the authors' names in your bibtex, and the citations should change :)

github.com/tpimentelms/...

Inline citations with only first author name, or first two co-first author names.

4 23 85

sarapapi.bsky.social @sarapapi.bsky.social · May 9

I am honored to have received this award today! 🎊

MT Group at FBK @fbk-mt.bsky.social · May 9

🎉 Excited to share that our @sarapapi.bsky.social has won the 2024 Best PhD Award from the Information and Engineering Doctoral School for her thesis “Direct Speech Translation in Constrained Contexts: The Simultaneous and Subtitling Scenarios.”

#nlproc #speech #speechprocessing #speechtranslation

4

Reposted

IWSLT @iwslt.bsky.social · Apr 3

The evaluation period has begun for our shared tasks!

The test data is now available on our website, and submissions are due Tuesday April 15! ⏰

Please email task organizers or the google group with any questions 🥳

4 6

sarapapi.bsky.social @sarapapi.bsky.social · Apr 1

📢 The evaluation period of the Instruction Following task at
@iwslt.bsky.social just started!

🖥️ Consider submitting your speech-to-text system!

The outputs can be easily uploaded on the SPEECHM platform developed in the Meetween project (www.meetween.eu)!
➡️ iwslt2025.speechm.cloud.cyfronet.pl

iwslt2025.speechm.cloud.cyfronet.pl

5 9

sarapapi.bsky.social @sarapapi.bsky.social · Mar 25

Thanks a lot! @deboranozza.bsky.social already added me to the channel 😊

2

sarapapi.bsky.social @sarapapi.bsky.social · Mar 19

I'm thrilled to be one of the speakers at the next MT Marathon in Helsinki 🚀

I look forward to sharing insights on automatic translation and related topics with our community!

Helsinki NLP @helsinki-nlp.bsky.social · Mar 18

Call for participation: We just opened the registration for this year's MT Marathon in August in Helsinki, Finland: blogs.helsinki.fi/language-tec..., featuring:

- Ayodele Awokoya
- Wilker Aziz
- Marta Costa-Jussa
- Barry Haddow
- Amit Moryosse
- Sara Papi
- Jörg Tiedemann
- Marco Turchi

blogs.helsinki.fi

2

sarapapi.bsky.social @sarapapi.bsky.social · Mar 17

❤️

1 1

sarapapi.bsky.social @sarapapi.bsky.social · Feb 20

Glad to see that the model weights of the new Step-Audio, a speech foundation model + large language model (+ speech decoder) architecture, are published under open licenses! 🆓

arxiv.org/abs/2502.11946

Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction

Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such as high costs in vo...

arxiv.org

4

Reposted

GITT 2025 @gitt-workshop.bsky.social · Feb 13

As if you needed more reasons to submit to #GITT2025:
🔑🎵 Cristina Anselmi, video game #localization & #AI expert with a focus on #inclusive #language will be our keynote speaker!
💸Registration fees are on the MTSummit website and you can register just for GITT if you so choose 😎
👀 See you there! 👀

9 13

sarapapi.bsky.social @sarapapi.bsky.social · Jan 23

I'm happy to share that our paper "Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison" has been accepted at @naaclmeeting.bsky.social 2025! #NAACL2025

@mgaido91.bsky.social 👏

📃 Preprint: arxiv.org/abs/2501.02370
⏰ Code will be released soon

#NLProc #Speech

Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison

Following the remarkable success of Large Language Models (LLMs) in NLP tasks, there is increasing interest in extending their capabilities to speech -- the most common form in communication. To integ...

arxiv.org

3 10

Reposted

GITT 2025 @gitt-workshop.bsky.social · Jan 22

Hello world! 👋 We're coming out of hibernation to bring you this happy news:
1) We're organising the 3rd edition of GITT at #MTSummit! Working on #gender & #translation #technology? We'll see you there!
2) We're moving away from Twitter, so share the news and help us find old and new GITT friends!

a polar bear cub is laying in a pile of branches .

ALT: a polar bear cub is laying in a pile of branches .

media.tenor.com

15 27

Reposted

MT Group at FBK @fbk-mt.bsky.social · Jan 16

🙌 All members of our group are now on Bluesky! 🙌

You can find all of us in this starter pack 👇

5 6