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 @lina97337786: "Towards a Deep Understanding of Multilingual End-to-End Speech Translation" by @hrsun42, @YikunLei et al., Findings EMNLP 2023.
#NLP #NLProc #EMNLP2023 #speech #translation #multilingual
🎉 AI-GAP workshop wrapped up yesterday!
Huge thanks to the participants, speakers, and organizers -- we were very happy, as you can see :)
@donatellado @BeatriceSavoldi @costanzalfieri @ECappu Clara Punzi & Laura State
🎊 I'm very happy to share that the paper "Direct Speech Translation for Automatic Subtitling" accepted by the #TACL journal is now published and available at:
#NLP #NLProc #subtitling #speech #translation
📢 @BeatriceSavoldi from @fbk_mt (@FBK_research) is co-organizing the AI GAP Workshop, held in collaboration with @Unipisa, @univaq, and @scuolanormale!
👉 Check the website for more information:
#AI #ArtificialIntelligence #AlgorithmicBias