@inproceedings{deshpande-etal-2022-stereokg,
title = {StereoKG: Data-Driven Knowledge Graph Construction For Cultural Knowledge and Stereotypes},
author = {Awantee Deshpande and Dana Ruiter and Marius Mosbach and Dietrich Klakow andKanika Narang and Aida Mostafazadeh Davani and Lambert Mathias and Bertie Vidgen and Zeerak Talat},
url = {https://aclanthology.org/2022.woah-1.7/},
doi = {https://doi.org/10.18653/v1/2022.woah-1.7},
year = {2022},
date = {2022},
booktitle = {Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)},
pages = {67-78},
publisher = {Association for Computational Linguistics},
address = {Seattle, Washington (Hybrid)},
abstract = {<div class="card bg-light mb-2 mb-lg-3">
<div class="card-body acl-abstract">Analyzing ethnic or religious bias is important for improving fairness, accountability, and transparency of natural language processing models. However, many techniques rely on human-compiled lists of bias terms, which are expensive to create and are limited in coverage. In this study, we present a fully data-driven pipeline for generating a knowledge graph (KG) of cultural knowledge and stereotypes. Our resulting KG covers 5 religious groups and 5 nationalities and can easily be extended to more entities. Our human evaluation shows that the majority (59.2%) of non-singleton entries are coherent and complete stereotypes. We further show that performing intermediate masked language model training on the verbalized KG leads to a higher level of cultural awareness in the model and has the potential to increase classification performance on knowledge-crucial samples on a related task, i.e., hate speech detection.</div>
</div>},
pubstate = {published},
type = {inproceedings}
}