Tasks that ultimately require knowledge-based multimedia techniques (content-oriented search, assessment, abstracting, etc.) are still to a major extent carried out manually. PATExpert’s overall scientific goal is to change the paradigm currently followed for patent processing from textual (viewing patents as text blocks enriched by “canned” picture material, sequences of morpho-syntactic tokens, or collections of syntactic structures) to semantic (viewing patents as multimedia knowledge objects) processing. PATExpert developed a multimedia content representation formalism based on Semantic Web technologies for selected technology areas and investigate the retrieval, classification, multilingual generation of concise patent information, assessment and visualization of patent material encoded in this formalism, taking the information needs of all user types as defined in a user typology into account. PATExpert’s technological goal was to develop a showcase that demonstrates the viability of PATExpert’s approach to content representation for real applications. The composition and the competence of the Consortium ensured the achievement of these goals.
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