450 citations · 575 across the 28 of their papers we have counts for
29 papers
Feedback Guidance of Diffusion Models
Felix Koulischer, Florian Handke, Johannes Deleu +2
While Classifier-Free Guidance (CFG) has become standard for improving sample fidelity in conditional diffusion models, it can harm diversity and induce memorization by applying co…
Dynamic Negative Guidance of Diffusion Models
Felix Koulischer, Johannes Deleu, Gabriel Raya +2
Negative Prompting (NP) is widely utilized in diffusion models, particularly in text-to-image applications, to prevent the generation of undesired features. In this paper, we show…
Clinical Reasoning over Tabular Data and Text with Bayesian Networks
Paloma Rabaey, Johannes Deleu, Stefan Heytens +1
Bayesian networks are well-suited for clinical reasoning on tabular data, but are less compatible with natural language data, for which neural networks provide a successful framewo…
Exploring the Temperature-Dependent Phase Transition in Modern Hopfield Networks
Felix Koulischer, Cédric Goemaere, Tom van der Meersch +2
The recent discovery of a connection between Transformers and Modern Hopfield Networks (MHNs) has reignited the study of neural networks from a physical energy-based perspective. T…
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…
Accelerating Hopfield Network Dynamics: Beyond Synchronous Updates and Forward Euler
Cédric Goemaere, Johannes Deleu, Thomas Demeester
The Hopfield network serves as a fundamental energy-based model in machine learning, capturing memory retrieval dynamics through an ordinary differential equation (ODE). The model'…
Career Path Prediction using Resume Representation Learning and Skill-based Matching
Jens-Joris Decorte, Jeroen Van Hautte, Johannes Deleu +2
The impact of person-job fit on job satisfaction and performance is widely acknowledged, which highlights the importance of providing workers with next steps at the right time in t…
Distractor generation for multiple-choice questions with predictive prompting and large language models
Semere Kiros Bitew, Johannes Deleu, Chris Develder +1
Large Language Models (LLMs) such as ChatGPT have demonstrated remarkable performance across various tasks and have garnered significant attention from both researchers and practit…
Extreme Multi-Label Skill Extraction Training using Large Language Models
Jens-Joris Decorte, Severine Verlinden, Jeroen Van Hautte +3
Online job ads serve as a valuable source of information for skill requirements, playing a crucial role in labor market analysis and e-recruitment processes. Since such ads are typ…
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…
BioDEX: Large-Scale Biomedical Adverse Drug Event Extraction for Real-World Pharmacovigilance
Karel D'Oosterlinck, François Remy, Johannes Deleu +7
Timely and accurate extraction of Adverse Drug Events (ADE) from biomedical literature is paramount for public safety, but involves slow and costly manual labor. We set out to impr…
TempEL: Linking Dynamically Evolving and Newly Emerging Entities
Klim Zaporojets, Lucie-Aimee Kaffee, Johannes Deleu +3
In our continuously evolving world, entities change over time and new, previously non-existing or unknown, entities appear. We study how this evolutionary scenario impacts the perf…
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…
Learning to Reuse Distractors to support Multiple Choice Question Generation in Education
Semere Kiros Bitew, Amir Hadifar, Lucas Sterckx +3
Multiple choice questions (MCQs) are widely used in digital learning systems, as they allow for automating the assessment process. However, due to the increased digital literacy of…
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…
CookDial: A dataset for task-oriented dialogs grounded in procedural documents
Yiwei Jiang, Klim Zaporojets, Johannes Deleu +2
This work presents a new dialog dataset, CookDial, that facilitates research on task-oriented dialog systems with procedural knowledge understanding. The corpus contains 260 human-…
Towards Consistent Document-level Entity Linking: Joint Models for Entity Linking and Coreference Resolution
Klim Zaporojets, Johannes Deleu, Yiwei Jiang +2
We consider the task of document-level entity linking (EL), where it is important to make consistent decisions for entity mentions over the full document jointly. We aim to leverag…
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…
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…
Solving Arithmetic Word Problems by Scoring Equations with Recursive Neural Networks
Klim Zaporojets, Giannis Bekoulis, Johannes Deleu +2
Solving arithmetic word problems is a cornerstone task in assessing language understanding and reasoning capabilities in NLP systems. Recent works use automatic extraction and rank…
Block-wise Dynamic Sparseness
Amir Hadifar, Johannes Deleu, Chris Develder +1
Neural networks have achieved state of the art performance across a wide variety of machine learning tasks, often with large and computation-heavy models. Inducing sparseness as a…
Sub-event detection from Twitter streams as a sequence labeling problem
Giannis Bekoulis, Johannes Deleu, Thomas Demeester +1
This paper introduces improved methods for sub-event detection in social media streams, by applying neural sequence models not only on the level of individual posts, but also direc…
Definition and evaluation of model-free coordination of electrical vehicle charging with reinforcement learning
Nasrin Sadeghianpourhamami, Johannes Deleu, Chris Develder
Initial DR studies mainly adopt model predictive control and thus require accurate models of the control problem (e.g., a customer behavior model), which are to a large extent unce…
Predefined Sparseness in Recurrent Sequence Models
Thomas Demeester, Johannes Deleu, Fréderic Godin +1
Inducing sparseness while training neural networks has been shown to yield models with a lower memory footprint but similar effectiveness to dense models. However, sparseness is ty…