Alert button
Picture for Dennis Ulmer

Dennis Ulmer

Alert button

Non-Exchangeable Conformal Language Generation with Nearest Neighbors

Feb 01, 2024
Dennis Ulmer, Chrysoula Zerva, André F. T. Martins

Viaarxiv icon

Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk

Jan 10, 2024
Dennis Ulmer, Elman Mansimov, Kaixiang Lin, Justin Sun, Xibin Gao, Yi Zhang

Viaarxiv icon

Non-Exchangeable Conformal Risk Control

Oct 02, 2023
António Farinhas, Chrysoula Zerva, Dennis Ulmer, André F. T. Martins

Viaarxiv icon

Uncertainty in Natural Language Generation: From Theory to Applications

Jul 28, 2023
Joris Baan, Nico Daheim, Evgenia Ilia, Dennis Ulmer, Haau-Sing Li, Raquel Fernández, Barbara Plank, Rico Sennrich, Chrysoula Zerva, Wilker Aziz

Figure 1 for Uncertainty in Natural Language Generation: From Theory to Applications
Figure 2 for Uncertainty in Natural Language Generation: From Theory to Applications
Viaarxiv icon

State-of-the-art generalisation research in NLP: a taxonomy and review

Oct 10, 2022
Dieuwke Hupkes, Mario Giulianelli, Verna Dankers, Mikel Artetxe, Yanai Elazar, Tiago Pimentel, Christos Christodoulopoulos, Karim Lasri, Naomi Saphra, Arabella Sinclair, Dennis Ulmer, Florian Schottmann, Khuyagbaatar Batsuren, Kaiser Sun, Koustuv Sinha, Leila Khalatbari, Maria Ryskina, Rita Frieske, Ryan Cotterell, Zhijing Jin

Figure 1 for State-of-the-art generalisation research in NLP: a taxonomy and review
Figure 2 for State-of-the-art generalisation research in NLP: a taxonomy and review
Figure 3 for State-of-the-art generalisation research in NLP: a taxonomy and review
Figure 4 for State-of-the-art generalisation research in NLP: a taxonomy and review
Viaarxiv icon

deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks

Apr 14, 2022
Dennis Ulmer, Christian Hardmeier, Jes Frellsen

Figure 1 for deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
Figure 2 for deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
Figure 3 for deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
Figure 4 for deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks
Viaarxiv icon

Experimental Standards for Deep Learning Research: A Natural Language Processing Perspective

Apr 13, 2022
Dennis Ulmer, Elisa Bassignana, Max Müller-Eberstein, Daniel Varab, Mike Zhang, Christian Hardmeier, Barbara Plank

Figure 1 for Experimental Standards for Deep Learning Research: A Natural Language Processing Perspective
Figure 2 for Experimental Standards for Deep Learning Research: A Natural Language Processing Perspective
Figure 3 for Experimental Standards for Deep Learning Research: A Natural Language Processing Perspective
Viaarxiv icon

A Survey on Evidential Deep Learning For Single-Pass Uncertainty Estimation

Oct 06, 2021
Dennis Ulmer

Figure 1 for A Survey on Evidential Deep Learning For Single-Pass Uncertainty Estimation
Figure 2 for A Survey on Evidential Deep Learning For Single-Pass Uncertainty Estimation
Figure 3 for A Survey on Evidential Deep Learning For Single-Pass Uncertainty Estimation
Figure 4 for A Survey on Evidential Deep Learning For Single-Pass Uncertainty Estimation
Viaarxiv icon

Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs

Jan 03, 2021
Dennis Ulmer

Figure 1 for Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs
Figure 2 for Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs
Figure 3 for Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs
Figure 4 for Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs
Viaarxiv icon

Know Your Limits: Monotonicity & Softmax Make Neural Classifiers Overconfident on OOD Data

Dec 11, 2020
Dennis Ulmer, Giovanni Cinà

Figure 1 for Know Your Limits: Monotonicity & Softmax Make Neural Classifiers Overconfident on OOD Data
Figure 2 for Know Your Limits: Monotonicity & Softmax Make Neural Classifiers Overconfident on OOD Data
Viaarxiv icon