ProsperAMnet at the FinSim Task: Detecting hypernyms of financial concepts via measuring the information stored in sparse word representations

1 code implementation • FinNLP (COLING) 2020 • Gábor Berend, Norbert Kis-Szabó, Zsolt Szántó

Quasi-Multitask Learning: an Efficient Surrogate for Obtaining Model Ensembles

no code implementations • EMNLP (sustainlp) 2020 • Norbert Kis-Szabó, Gábor Berend

We propose the technique of quasi-multitask learning (Q-MTL), a simple and easy to implement modification of standard multitask learning, in which the tasks to be modeled are identical.

Frustratingly easy quasi-multitask learning

no code implementations • 25 Sep 2019 • Gábor Berend, Norbert Kis-Szabó

We propose the technique of quasi-multitask learning (Q-MTL), a simple and easy to implement modification of standard multitask learning, in which the tasks to be modeled are identical.