Erik Velldal

Using Gender- and Polarity-Informed Models to Investigate Bias

2021

In this work we explore the effect of incorporating demographic metadata in a text classifier trained on top of a pre-trained transformer language model. More specifically, we add information about the gender of critics and …

Compositional Generalization with Grounded Language Models

2024 · arXiv (Cornell University)

Grounded language models use external sources of information, such as knowledge graphs, to meet some of the general challenges associated with pre-training. By extending previous work on compositional generalization in semantic parsing, we allow for …