Prof. Dr. Iryna Gurevych
Description
The open-access dissemination of pretrained language models through online repositories has led to a democratization of state-of-the-art natural language processing (NLP) research.
This also allows people outside of NLP to use such models and adapt them to specific use-cases.
However, a certain amount of technical proficiency is still required which is an entry barrier for users who want to apply these models to a certain task but lack the necessary knowledge or resources.
In this talk, I will present the AdapterHub Playground application. It was developed to overcome this gap by providing a tool which allows researchers to conduct text classification without writing a single line of code.
It provides an intuitive interface for training, prediction, and analysis of textual data for a variety of NLP tasks.
Besides presenting the tool’s architecture, I will demonstrate its advantages with a prototypical use-case, where we show that predictive performance can easily be increased in a few-shot learning scenario.
Textual big data stores all of humanity’s knowledge: only tapping into this knowledge with the help of AI and NLP enables humanity to utilize it effectively and responsibly to the benefit of all.
Biography
Iryna Gurevych (PhD 2003, U. Duisburg-Essen, Germany) is professor of Computer Science and Natural Language Processing (NLP). She is director of the Ubiquitous Knowledge Processing (UKP) Lab at the Technical University (TU) of Darmstadt in Germany. She joined TU Darmstadt in 2005 (tenured as full professor in 2009). Her main research interest is machine learning for large-scale language understanding and applications of big data in NLP. She has co-founded the field of computational argumentation involving fact-checking and decision-making support. Iryna’s work received numerous awards, e.g. the first Hessian LOEWE Distinguished Chair (German: LOEWE-Spitzenprofessur) in 2021, a highly competitive Lichtenberg-Professorship Award from the Volkswagen Foundation, and a DFG Emmy-Noether Young Researcher’s Excellence Career Award. She has been elected to be the future president (2023) of the international Association for Computational Linguistics (ACL) and is an ACL fellow 2020.