Regex in a Time of Deep Learning: The Role of an Old Technology in Age Discrimination Detection in Job Advertisements
This work addresses age discrimination detection in job ads, which is an incremental improvement by comparing old and new methods.
The paper tackles the problem of detecting illegal age discrimination in job advertisements, finding that regex approaches remain strong performers while neural embeddings could address their limitations.
Deep learning holds great promise for detecting discriminatory language in the public sphere. However, for the detection of illegal age discrimination in job advertisements, regex approaches are still strong performers. In this paper, we investigate job advertisements in the Netherlands. We present a qualitative analysis of the benefits of the 'old' approach based on regexes and investigate how neural embeddings could address its limitations.