Current projects
Towards Complex Reasoning in LLMs
CUNE-IIIF-ORM: Towards an Internationally Image Interoperable Corpus of Cuneiform Tablets
Dutch Automated Writing evaluation through NLP
Displays of Desire: Imagineering Consumption in Comedies of the Low Countries (1650-1725)
Explainable Personalised Automated Writing Feedback for L2 Dutch
Modeling empathy in multimodal conversational agents
Fine-tuning GPT models for lexicography
Machine translation to inform asylum seekers
Machine translation evaluation in the context of scholarly communication
Political Argument Recognition and Analysis on Social Media
POLAR: Political Argument Recognition and Analysis on Social Media
Researching Stereotypes towards LGBTQIA+ Community Members with Multilingual Natural Language Processing
Past projects
Automatic Leaflet Optimizer
Automatic Monitoring for Cyberspace Applications
Annual Report Characterization In Varieties of English
Assessing The Comprehensibility of Automatic Translations
Bantu Corpus Linguistics
Corpus of Historical Low German
CLARIAH-VL: Open Humanities Service Infrastructure
Comprehensive Integration of Linguistic Features in a Human Inspired Speech Recognition Architecture
Modelling common-sense knowledge in automatic irony detection
SemEval-2 Task#3: Cross-Lingual Word Sense Disambiguation Task
Measuring Orthographic and Semantic Similarity between Byzantine Greek Epigrams
Dutch Parallel Corpus
Developing User-centred Approaches to Technological Innovation in Literary Translation
Dutch Online Media Analysis
Emotion detection for Dutch
Unrestricted Cross-Document Event Coreference for Dutch
Extraction of Parallel Elements from Comparable Texts
Extracting Terminology Automatically from Comparable Texts
An Automated Clarity Tool for Dutch and English Discourse
Merging writing process data with lexica
Intelligent Vocabulary and Example Selection for Spanish vocabulary learning
Low-Shot Cross-Lingual Knowledge Transfer
MAchine Translation Evaluation Online
Modelling Emotion TRajectories in Customer Service dialogues
MuST: Multilingual Corpora for the automatic Structuring of Terms.
Machine translation with User-specific Training and User-specific Adaptation for Literary texts: impact on Individual Style in Translation
Diversity in the News through Algorithmization
A readability Optimizer for Patient Information Leaflets
Parallel corpora for Dutch word sense disambiguation
Personalised AdveRtisements built from web Sources
Detection of topics, stance and argumentation in a social media corpus
Predicting Difficulty in Translation
Étude doublons et synonymes thésaurus APV