activity
20182023
most citedDesign of Negative Sampling Strategies for Distantly Supervised Skill Extraction

6 citations · 13 across the 6 of their papers we have counts for

collaborators

12 papers

cs.LG20231 cited

Training a Hopfield Variational Autoencoder with Equilibrium Propagation

Tom Van Der Meersch, Johannes Deleu, Thomas Demeester

On dedicated analog hardware, equilibrium propagation is an energy-efficient alternative to backpropagation. In spite of its theoretical guarantees, its application in the AI domai…

cs.CL20231 cited

Learning from Partially Annotated Data: Example-aware Creation of Gap-filling Exercises for Language Learning

Semere Kiros Bitew, Johannes Deleu, A. Seza Doğruöz +2

Since performing exercises (including, e.g., practice tests) forms a crucial component of learning, and creating such exercises requires non-trivial effort from the teacher, there…

cs.CL2022

EduQG: A Multi-format Multiple Choice Dataset for the Educational Domain

Amir Hadifar, Semere Kiros Bitew, Johannes Deleu +2

We introduce a high-quality dataset that contains 3,397 samples comprising (i) multiple choice questions, (ii) answers (including distractors), and (iii) their source documents, fr…

cs.CL20226 cited

Design of Negative Sampling Strategies for Distantly Supervised Skill Extraction

Jens-Joris Decorte, Jeroen Van Hautte, Johannes Deleu +2

Skills play a central role in the job market and many human resources (HR) processes. In the wake of other digital experiences, today's online job market has candidates expecting t…

cs.CL2021

Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution

Severine Verlinden, Klim Zaporojets, Johannes Deleu +2

We consider a joint information extraction (IE) model, solving named entity recognition, coreference resolution and relation extraction jointly over the whole document. In particul…

cs.CL2020

DWIE: an entity-centric dataset for multi-task document-level information extraction

Klim Zaporojets, Johannes Deleu, Chris Develder +1

This paper presents DWIE, the 'Deutsche Welle corpus for Information Extraction', a newly created multi-task dataset that combines four main Information Extraction (IE) annotation…