Where: Sala conferenze (3th floor)
When: 27/11/2023 11:00
Matthias is a PhD student in the Semantic Computing Group at Bielefeld University (Germany) supervised by Philipp Cimiano. He works on systems to improve online discussions with a particular focus on perspectives and human label variation. From April to June 2022 he visited the MilaNLP Lab at Bocconi University (Italy) to work on related problems in modeling sociodemographics and continues to collaborate with the group.
Abstract:
Annotators, like we all, are shaped to some extent by their membership in social groups of various types. Some groups are formed based on socially-relevant categories, like age or gender, others can be more local and temporary. For example, the group of all annotators in the annotation process is just that, a group. If groups have an impact on us, can we include them in our models to better capture individual perspectives?
I will present results from two recent works to provide some tentative answers to this question. In one case we find that groups based on sociodemographics might be too coarse to be informative [1]. In the other we see that it is beneficial to model the annotators of a dataset as a group and in relation to one another [2].