1
Recent research suggests that systematic generalization in natural language understanding remains a challenge for state-of-the-art …
Deep ensembles offer consistent performance gains, both in terms of reduced generalization error and improved predictive uncertainty …
This paper explores the capabilities of current transformer-based language models for program evaluation of simple functional …
Large pre-trained language models for textual data have an unconstrained output space; at each decoding step, they can produce any of …
Explainability for machine learning models has gained considerable attention within the research community given the importance of …
Inferring objects and their relationships from an image in the form of a scene graph is useful in many applications at the intersection …
Remote sensing and automatic earth monitoring are key to solve global-scale challenges such as disaster prevention, land use …
Recent metabolomics measurement devices, such as mass spectrometers, produce extremely high-dimensional data. Together with small …
Recent neural text-to-SQL models can effectively translate natural language questions to corresponding SQL queries on unseen databases. …
Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language …