While modern language models do a great job at finding documents, extracting information from them and generating naturally sounding language, the progress in helping humans read, connect, and make sense of interrelated long texts has been very much limited.<\/p> \n \n
Funded by the European Research Council, the InterText project brings natural language processing (NLP) forward by developing a general framework for modeling and analyzing fine-grained relationships between texts – intertextual relationships. This crucial milestone for AI would allow tracing the origin and evolution of texts and ideas and enable a new generation of AI applications for text work and critical reading.<\/p> \n \n
This talk will elaborate their intertextual approach to NLP using the scientific domain as a prototypical, challenging application area. Specifically, they will highlight two lines of our work. The first one is related to task design, practical applications and intricacies of data collection in the peer-review domain. The second one is about scientific text generation targeting (i) citation text and (ii) attitude and theme-guided rebuttals. To conclude, they will briefly describe our ongoing efforts towards fine-grained linking of multiple documents, temporal analysis of scientific datasets and research novelty modeling.<\/p> \n \n
<\/p> \n \n
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 of Darmstadt in Germany. In addition, she is an adjunct professor at MBZUAI in Abu-Dhabi, UAE and an affiliated professor at INSAIT in Sofia, Bulgaria. Her main research interests are in machine learning for large-scale language understanding and text semantics.<\/p> \n \n
Iryna’s work has received numerous awards. Those include the ACL fellow award 2020, the first-ever Hessian LOEWE Distinguished Chair award (2,5 mil. Euro) in 2021 and an ERC Advanced Grant in 2022 (2,5 Mil. Euro). Iryna is co-director of the NLP program within ELLIS, a European network of excellence in machine learning. In 2023, she was the president of the Association for Computational Linguistics (ACL).<\/p> \n \n
<\/p> \n \n
May 8, 2024. 11:30am<\/p> \n \n
<\/p> \n \n
Universitätstraße 32.101, Campus Vaihingen of the University of Stuttgart <\/p> \n \n
<\/p> \n \n