Hasso-Plattner-Institut
 
    • de
 

Gonçalo Mordido

Ph.D. Student in Deep Learning

Multimedia and Machine Learning Research Group

Hasso-Plattner-Institut (HPI) für
Digital Engineering gGmbH
Universität Potsdam
Prof.-Dr.-Helmert-Str. 2-3
14482 Potsdam
Germany

office:      H-1.22
phone:    +49 (0)331-5509-516
fax:         +49 (0)331-5509-325
email:     goncalo.mordido(at)hpi.de

LinkedIn profile

Research Interests

  • Deep Learning
  • Generative Adversarial Models
  • Natural Language Processing

Current Projects

Deep Learning for Enterprise NLP Applications

Project partner: SAP AG

In this project we will develop a framework for building general-applicable as well as domain-specific NLP models by using state-of-the-art deep learning technology. The research problem on textual representation learning will be studied intended to find the most efficient solution for deep neural network design, and system implementation. The evaluation protocol will be defined and developed for the qualitative and quantitative evaluation.

Previous Projects

Cognitus

Project partners: BBC R&D, QMUL, FCT/UNL, Forthnet, VITEC, FORTH, ARRIS

The COGNITUS project aims to combine the advances in UHD broadcasting technologies with the explosion of UGC in order to create new interactive, immersive modes of production. COGNITUS is a joint research project comprising eight European participants, led by BBC R&D. The project is intended to optimise how UHD content is produced and distributed, by capitalising upon the knowledge of professional producers, the ubiquity of UGC and the power of interactive networked social creativity.

Previous Publications

2017

Activities

  • Innovation talk on "Dialogue Generation with Generative Adversarial Networks" at SAP TechEd 2017 in Las Vegas, NV, USA [video]
  • Co-reviewer for IEEE International Conference on Big Data (IEEE Big Data 2017) in Boston, MA, USA
  • Poster presentation at the 25th European Signal Processing Conference (EUSIPCO 2017) in Kos Island, Greece