Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture delves into the ethical aspects of Natural Language Processing (NLP) systems, focusing on issues such as biases, toxicity, privacy, and disinformation. The instructor discusses real-world examples like the Tay chatbot and the implications of biased language models. The lecture explores the classification of harms from language models, the amplification of biases, and the challenges in coreference resolution. It also covers the risks of leaking private information and inferring sensitive data from NLP models. The session concludes with a critical examination of the potential dangers of deploying language models for disinformation purposes and the importance of considering ethical implications in NLP development.