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.

翻译：深入学习对于发现公共领域的歧视性语言很有希望,然而,为了发现在招聘广告中非法的年龄歧视,Regex方法仍然表现良好。我们在本文件中调查荷兰的招聘广告。我们根据regexes对“老”方法的好处进行了定性分析,并调查神经嵌入如何解决其局限性。