diff --git a/content/pages/events/seminars/2024-10-09/index.md b/content/pages/events/seminars/2024-10-09/index.md new file mode 100644 index 000000000..18c817ed7 --- /dev/null +++ b/content/pages/events/seminars/2024-10-09/index.md @@ -0,0 +1,11 @@ +--- +lecturer: "Rob van der Goot from IT University of Copenhagen" +title: "Robustness in NLP: challenges and opportunities" +type: seminar +date: 2024-10-09 +duration: "2 hours" +venue: "Gothenburg and online" +slides: "Rob van der Goot 9.10.2024.pdf" +--- + +Abstract: This talk will cover a variety of setups and approaches to robustness in NLP. I will start by giving an overview (including limitations) of the task of lexical normalization: the conversion of social media data to its canonical form. Next, I will discuss the challenges in using multi-task learning to improve performance in low-resource setups. Finally, I will unveil remaining challenges in the first steps of the NLP pipeline: language identification and tokenization (i.e. word segmentation): are these tasks really solved?, and if no: what are still the open challenges that we should focus on in the future?