AI seminar: Towards Trustworthy Natural Language Processing
At this seminar, Jasmijn Bastings, Google Amsterdam, will present work done at Google aimed to make progress towards a more trustworthy natural language processing.
In this talk I will present work done at Google aimed to make progress towards a more trustworthy natural language processing. We will first establish what trustworthiness and trust mean, and when we can say that a system is trustworthy. We'll then discuss what desiderata a trustworthy NLP system should meet, before we look at recent work done at Google towards this end.
Jasmijn Bastings (she/her) is a researcher at Google Amsterdam, having joined Google in Berlin late 2019. She holds a PhD from ILLC, University of Amsterdam, on the topic of Interpretable and Linguistically-informed Deep Learning for NLP. Recently, Jasmijn has been focusing on explainability, fairness and robustness within natural language processing. She is also one of the organizers of BlackBoxNLP: Analyzing and interpreting neural networks for NLP, a workshop collocated with EMNLP 2021.
This seminar is a part of the AI Seminar Series organised by SCIENCE AI Centre. The series highlights advances and challenges in research within Machine Learning, Data Science, and AI. Like the AI Centre itself, the seminar series has a broad scope, covering both new methodological contributions, ground-breaking applications, and impacts on society.