Joris Baan

4 papers · 2019–2024 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (15) 🐣 Hot Topic Early Bird ❓ The Questioner (2)

Venues

EMNLP (2) ACL (1) EACL (1)

Top co-authors

Raquel Fernández (3) Wilker Aziz (3) Barbara Plank (3) Dennis Ulmer (1) Tim Baumgärtner (1) Elia Bruni (1) Dieuwke Hupkes (1) David Rau (1) Mario Giulianelli (1) Mitja Nikolaus (1)

Research topics

Machine Learning (4) Optimization & Theory (4) Artificial Intelligence (3) Bayesian & Probabilistic (2) Core Methods (2) Deep Learning (1) Architectures (1) Core AI (1) Learning Types (1) Techniques (1)

Keywords

uncertainty quantification (3) probabilistic modeling (2) model calibration (1) attention mechanism (1) natural language generation (1) text generation (1) probability estimation (1) probabilistic prediction (1) probability calibration (1) recurrent neural network (1) sampling method (1) parameter space (1) aleatoric uncertainty (1) sequence-to-sequence model (1) sequence to sequence (1) human disagreement (1) classifier evaluation (1) neural network (1) class frequency (1) predictive probability (1)

Papers

Interpreting Predictive Probabilities: Model Confidence or Human Label Variation? EACL 2024 What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability EMNLP 2023 Stop Measuring Calibration When Humans Disagree EMNLP 2022 On the Realization of Compositionality in Neural Networks ACL 2019