The main concept of the project EuroSentiment was to provide a shared language resource pool for fostering sentiment analysis. To this end, a detailed collection of requirements of language resource providers and users was performed with the aim of satisfying their needs in terms of multilingual, quality and domain coverage. Interoperability was achieved by cleaning, aligning, and integrating various resources, resulting in the establishment of a seamless and homogeneous interface.
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
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
Late update, but we had two great talks last month!
#MachineTranslation #FBK #NLProc #GenderBias #SpeechSynthesis
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
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
⭐ 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.