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.
ππΌ Excited to share our work on Speech Foundation Model for data crowdsourcing at COLING 2025 ππΌ
Our co-author Laurent Besacier (@laurent_besacie) at NAVER LABS Europe will be presenting -- don't miss it.
ππΌ Details: https://mt.fbk.eu/1-paper-accepted-at-coling-2025
Exciting news: @iwslt is co-located with #ACL2025NLP again this year! π
Interested in speech processing? Check out the new task on instruction following β any model can participate! π
π
Data release: April 1
β³ Submission deadline: April 15
Donβt miss it! π¬ #NLP #SpeechTech
Weekly pick from the #MeetweenScientificWatch: βVideo-SALMONN: Speech-enhanced audio-visual large language modelsβ β Redefining video comprehension with speech-aware AV-LLMs and groundbreaking QA accuracy. π₯π€π€
Iβm glad to announce that our work βHow "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?β has been accepted at the Transactions of @aclanthology (TACL)! π
The preprint is available here: