activity
20192022
most citeddeep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks

19 citations · 34 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CL2022

Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity

Dennis Ulmer, Jes Frellsen, Christian Hardmeier

We investigate the problem of determining the predictive confidence (or, conversely, uncertainty) of a neural classifier through the lens of low-resource languages. By training mod…

cs.LG202219 cited

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

Dennis Ulmer, Christian Hardmeier, Jes Frellsen

A lot of Machine Learning (ML) and Deep Learning (DL) research is of an empirical nature. Nevertheless, statistical significance testing (SST) is still not widely used. This endang…

cs.CL2021

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

Dennis Ulmer

In Recurrent Neural Networks (RNNs), encoding information in a suboptimal or erroneous way can impact the quality of representations based on later elements in the sequence and sub…

cs.LG2020

Know Your Limits: Uncertainty Estimation with ReLU Classifiers Fails at Reliable OOD Detection

Dennis Ulmer, Giovanni Cinà

A crucial requirement for reliable deployment of deep learning models for safety-critical applications is the ability to identify out-of-distribution (OOD) data points, samples whi…

cs.LG202015 cited

Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular Data

Dennis Ulmer, Lotta Meijerink, Giovanni Cinà

When deploying machine learning models in high-stakes real-world environments such as health care, it is crucial to accurately assess the uncertainty concerning a model's predictio…

cs.CL2019

Assessing incrementality in sequence-to-sequence models

Dennis Ulmer, Dieuwke Hupkes, Elia Bruni

Since their inception, encoder-decoder models have successfully been applied to a wide array of problems in computational linguistics. The most recent successes are predominantly d…