Question Answering (QA)
Question Answering (QA) is becoming more important than ever because of its ubiquitous deployment in search engines and AI-powered virtual assistants. In addition, it is an ideal benchmark for most Natural Language Understanding tasks such as information extraction, fact verification, and sentiment analysis, thanks to its flexible and human-friendly format. This talk will explore the most popular datasets, the current explainability methods, and the new trends in this field. We will conclude with a live demo of a new online platform for QA research (UKP-SQuARE), where users can effortlessly deploy, analyze, and compare different models.
Bio Iryna Gurevych
Iryna Gurevych (PhD 2003, U. Duisburg-Essen, Germany) is professor of Computer Science and director of the Ubiquitous Knowledge Processing (UKP) Lab at the Technical University (TU) of Darmstadt in Germany. Her main research interests are in Machine Learning for large-scale language understanding and text semantics. Iryna’s work has received numerous awards: the ACL fellow award 2020, the ever-first Hessian LOEWE Distinguished Chair award (2,5 mil. Euro) in 2021 and the ERC Advanced Grant in 2022. Iryna is co-director of the NLP program within ELLIS, a European network of excellence in Machine Learning. She is currently the vice-president of the Association of Computational Linguistics.
Bio Haritz Puerto
Haritz Puerto is a Ph.D. candidate in Machine Learning & Natural Language Processing at UKP Lab in TU Darmstadt, supervised by Prof. Iryna Gurevych. His main research interests are reasoning for Question Answering and Graph Neural Networks. Previously, he worked at the Coleridge Initiative, where he co-organized the Kaggle Competition Show US the Data. Before that, he got his master’s degree from the School of Computing at KAIST, where he was a research assistant at IR&NLP Lab and was advised by Prof. Sung-Hyon Myaeng.
Back to the Summer School 2022 overview