Fréderic Godin

Fréderic Godin

Auto-generated profile, based on publicly available information

Fréderic Godin

Ghent University Ghent Belgium

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2018 in Pattern Recognition Letters
Verified
Journal Article
Closed access
FGFréderic Godin
Fréderic Godin
JDJonas Degrave
Jonas Degrave
JDJoni Dambre
Joni Dambre
WNWesley De Neve
Wesley De Neve

16 October 2014
Verified
Book Chapter
Closed access
PDF file
FGFréderic Godin
Fréderic Godin
TNTom De Nies
Tom De Nies
CBChristian Beecks
Christian Beecks
LVLaurens De Vocht
Laurens De Vocht
WNWesley De Neve
Wesley De Neve
RWRik Van de Walle
Rik Van de Walle

1 January 2021
Verified
Conference Paper
Open access
PDF file
MRMaarten De Raedt
Maarten De Raedt
FGFréderic Godin
Fréderic Godin
PBPieter Buteneers
Pieter Buteneers
CDChris Develder
Chris Develder
TDThomas Demeester
Thomas Demeester
Maarten De Raedt, Fréderic Godin, Pieter Buteneers, Chris Develder, Thomas Demeester. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.

3 April 2019 in arXiv
Verified
Preprint
Open access
PDF file
FGFréderic Godin
Fréderic Godin
AKAnjishnu Kumar
Anjishnu Kumar
AMArpit Mittal
Arpit Mittal
In this paper, we investigate the challenges of using reinforcement learning agents for question-answering over knowledge graphs for real-world applications. We examine the performance metrics used by state-of-the-art systems and determine that they are inadequate for such settings. More specifically, they do not evaluate the systems correctly for situations when there is no answer available and thus agents optimized for these metrics are poor at modeling confidence. We introduce a simple new performance metric for evaluating question-answering agents that is more representative of practical usage conditions, and optimize for this metric by extending the binary reward structure used in prior work to a ternary reward structure which also rewards an agent for not answering a question rather than giving an incorrect answer. We show that this can drastically improve the precision of answered questions while only not answering a limited number of previously correctly answered questions. Employing a supervised learning strategy using depth-first-search paths to bootstrap the reinforcement learning algorithm further improves performance.