project . 2018 - 2023 . On going

FoTran

Found in Translation – Natural Language Understanding with Cross-Lingual Grounding
Open Access mandate for Publications European Commission
  • Funder: European CommissionProject code: 771113 Call for proposal: ERC-2017-COG
  • Funded under: H2020 | ERC | ERC-COG Overall Budget: 1,817,620 EURFunder Contribution: 1,817,620 EUR
  • Status: On going
  • Start Date
    01 Sep 2018
    End Date
    31 Aug 2023
  • Detailed project information (CORDIS)
  • Open Access mandate
    Research Data: No
Description
Natural language understanding is the "holy grail" of computational linguistics and a long-term goal in research on artificial intelligence. Understanding human communication is difficult due to the various ambiguities in natural languages and the wide range of contextual dependencies required to resolve them. Discovering the semantics behind language input is necessary for proper interpretation in interactive tools, which requires an abstraction from language-specific forms to language-independent meaning representations. With this project, I propose a line of research that will focus on the development of novel data-driven models that can learn such meaning re...
Description
Natural language understanding is the "holy grail" of computational linguistics and a long-term goal in research on artificial intelligence. Understanding human communication is difficult due to the various ambiguities in natural languages and the wide range of contextual dependencies required to resolve them. Discovering the semantics behind language input is necessary for proper interpretation in interactive tools, which requires an abstraction from language-specific forms to language-independent meaning representations. With this project, I propose a line of research that will focus on the development of novel data-driven models that can learn such meaning re...
Any information missing or wrong?Report an Issue