JUMAS addresses the need to build an infrastructure able to optimise the information workflow in order to facilitate later analysis. New models and techniques for representing and automatically extracting the embedded semantics derived from multiple data sources will be developed. The most important goal of the JUMAS system is to collect, enrich and share multimedia documents annotated with embedded semantic minimising manual transcription activity. JUMAS is tailored at managing situations in which multiple cameras and audio sources are used to record assemblies in which people debates and event sequences need to be semantically reconstructed for future consultations. The prototype of JUMAS will be tested interworking with legacy systems, but the system can be viewed as able to support business processes and problem-solving in a variety of domains.
Our pick of the week by @lina_conti: "Exploring NMT Explainability for Translators Using NMT Visualising Tools" by Gonzalez-Saez, @MariamNakhle, @MeLlamoJamesT, @raheel_qader, @didier_schwab, et al., 2024.
#NMT #NLP #NLProc #explainiableAI #XAI
Our pick of the week by @beomseok_lee_: "DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding" by Shon, @shinjiw_at_cmu, et al., 2024.
#SLU #speech #LLM
Our pick of the week by @BeatriceSavoldi: "Rethinking Model Evaluation as Narrowing the Socio-Technical Gap" by @QVeraLiao and @ZiangXiao, 2023.
#Human #HumanCentered #Model #Evaluation #ModelEvaluation #AI
📢Come and join our group!
We offer a fully funded 3-year PhD position with the IECS Doctorate School @UniTrento:
Speech Translation in the LLM Era (Area A6)
⏱️Deadline: August 5th, 2024, h 4.00pm (CEST)
📌Application Details: https://iecs.unitn.it/education/admission/call-for-application
#NLProc @FBK_research