AI Synergies

Speakers

Giannis Bekoulis

PhD student

Adversarial Perturbations for Joint Entity and Relation Extraction

The  goal  of  the  entity  recognition  and  relation  extraction  task  is  to  discover relational structures of entity mentions from unstructured texts. It is a central problem in information extraction since it is critical for tasks such as knowledge base population and question answering.  In this work, we focus on extending the training procedure of our newly proposed general purpose joint model for entity recognition and relation extraction with adversarial training.

Biography

On January 2016, Giannis joined the IDLab research group at the Information Technology department of Ghent University, as a Ph.D. student. As a part of the UGent Text-to-Knowledge research cluster within IDLab, Giannis focused on Natural Language Processing techniques for extracting useful information from unstructured text and applied machine learning and neural network methods for core Natural Language Processing problems.

Program

Gamay room
Research presentations ML
Day 3 - Nov 8th

Brewery of Ideas

AI Synergies is organized by VUB/ULB, BNVKI and Brewery of Ideas.

More info about our events