Info_ERA-NET

ERA-NET

The ERA-NET scheme emerged in the EU's Sixth Framework Programme for RTD to support cooperation and coordination of national activities, programmes and initiatives related to science, technology and innovation with the aim of strengthening the European Research Area (ERA).

In most ERA-NETs, ​​coordination has reached the point of being able to launch calls for grants for joint research projects. These are transnational calls to which common application, evaluation and selection procedures are applied for proposals, which have been developed and agreed upon by all participating agencies.

The projects presented are two/three years long, close to the market, and with the aim of covering the needs of the company.

Era-Nets can be in any field of Science and Technology. You can see data of the ERANETS in which Spain has participated in previous years here.

ERA-NET Projects

LIHLITH: Learning to interact with humans by lifelong interaction with humans

Specific programme: European Coordinated Research on Long-term Challenges in Information and Communication Sciences & Technologies ERA-NET (CHIST ERA)
UPV/EHU Partner Status: Partner
UPV/EHU PI: Eneko Agirre
Project start: 01/12/2017
Project end:   30/09/2020

Brief description:  A Lifelong Learning system learns different tasks sequentially, over time, getting better at solving future related tasks based on experience. LIHLITH will focus on human-computer dialogue, where each dialogue experience is used by the system to learn to better interact, based on the success (or failure) of previous interactions. The key insight is that the dialogue will be designed to produce a reward, allowing the chatbot system to know whether the interaction was successful or not. The reward will be used to train the domain and dialogue management modules of the chatbot, improving the performance, and reducing the development cost, both on a single target domain but specially when moving to new domains.

The research will be evaluated by publicly available benchmarks to allow comparison with other approaches in the state of the art. When possible, systems will participate in international comparative/competitive evaluations such as WOCHAT or SemEval. LIHLITH project will also develop and deliver evaluation protocols and benchmarks to allow public comparison and reproducibility based on crowdsourcing.

LIHLITH will rely on recent advance in multiple research disciplines, including, natural language processing, knowledge induction, reinforcement learning, deep learning, and lifelong learning.

info_masinformacionehurope

Contact information:

International R&D Office UPV/EHU
Email: proyectoseuropeos@ehu.es