Corpora

MCIF

by Sara Papi | Apr 17, 2026 | Corpora | 0

MCIF (Multimodal Crosslingual Instruction Following) is a multilingual human-annotated benchmark based on scientific talks that is designed to evaluate instruction-following in crosslingual, multimodal settings over both short-...

mGeNTE

by Beatrice Savoldi | Jan 13, 2025 | Corpora | 0

mGeNTE (Multilingual Gender-Neutral Translation Evaluation) is a natural, multilingual corpus designed to benchmark gender-neutral language and automatic translation.mGente is built upon European Parliament speech data extracted...

MOSEL

by Sara Papi | Oct 31, 2024 | Corpora | 0

The MOSEL corpus is a multilingual dataset collection including up to 950K hours of open-source speech recordings covering the 24 official languages of the European Union. We collect data by surveying labeled and unlabeled...

Speech-MASSIVE

by Beomseok Lee | Aug 21, 2024 | Corpora | 0

Spoken Language Understanding (SLU) involves interpreting spoken input using Natural Language Processing (NLP). Voice assistants like Alexa and Siri are real-world examples of SLU applications. The core tasks in SLU include...

WAGS

by Mauro Cettolo | Apr 30, 2024 | Corpora | 0

Ready-to-use version for MT research purposes of the multilingual transcriptions of TED talks

GenderCrawl

by Dennis Fucci | Oct 20, 2023 | Corpora | 0

Text corpora for Spanish, French, and Italian containing gendered words referring to the first-person speaker

INES

by Beatrice Savoldi | Oct 19, 2023 | Corpora | 0

The INclusive Evaluation Suite (INES) is a test set designed to assess MT systems ability to produce gender-inclusive translations for the German→English language pair. By design, each German source sentence in INES includes an...

GeNTE

by Beatrice Savoldi | Oct 9, 2023 | Corpora | 0

GeNTE (Gender-Neutral Translation Evaluation) is a natural, bilingual corpus designed to benchmark the ability of machine translation systems to generate gender-neutral translations. Built from European Parliament speeches,...

EC Short Clips

by Marco Gaido | Jul 7, 2023 | Corpora | 0

EC Short Clips is a test set dedicated to evaluate automatic subtitling systems.

EuroParl Interviews

by Marco Gaido | Jul 7, 2023 | Corpora | 0

EuroParl Interviews is a test set dedicated to evaluate automatic subtitling systems.

NEuRoparl-ST

by Matteo Negri | Jun 1, 2023 | Corpora | 0

Multilingual benchmark built from European Parliament speeches and annotated with Named Entities and Terminology

Heroes-ON-OFF

by Mauro Cettolo | May 30, 2023 | Corpora | 0

Annotation of dubbing segments based on the Heroes corpus

MT Group at FBK Follow

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

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 1 Like on Twitter 2064764921062056414 4 Twitter 2064764921062056414

Avatar MT Group at FBK @fbk_mt ·

9 Jun

Late update, but we had two great talks last month!

#MachineTranslation #FBK #NLProc #GenderBias #SpeechSynthesis

Reply on Twitter 2064343003892683056 Retweet on Twitter 2064343003892683056 Like on Twitter 2064343003892683056 1 Twitter 2064343003892683056

Avatar MT Group at FBK @fbk_mt ·

3 Jun

Our pick of the week by @dhairya_su47605

: "Scaling Laws for Precision" by @tanishqkumar07, Zachary Ankner, @bfspectorShiekh, @blake__bordelon, @Muennighoff, @mansiege, @CPehlevan, Christopher R´e, @AdtRaghunathan

📰

#Quantization #LLM #ScalingLaw

Dhairya Suman @dhairya_su47605

Pick of the week @fbk_mt
Super interesting paper on the limitations of quantization, demonstrating how post-training quantization scales poorly in data.

https://arxiv.org/abs/2411.04330

Reply on Twitter 2062203374712344946 Retweet on Twitter 2062203374712344946 1 Like on Twitter 2062203374712344946 4 Twitter 2062203374712344946

Avatar MT Group at FBK @fbk_mt ·

27 May

⭐ For our #PickOfTheWeek, this paper explores an important question for modern speech AI:

🎙️ Which Evaluation for Which Speech Model?
👥 Authors: @Maureendss , @EeshanDhekane

Speech foundation models are evolving rapidly, but evaluation practices are still fragmented.

Reply on Twitter 2059703767570780492 Retweet on Twitter 2059703767570780492 Like on Twitter 2059703767570780492 2 Twitter 2059703767570780492