Can computers learn to write poetry in particular styles, or to summarize historical documents using more modern language? These and other subjects will be discussed in "Text Generation for the Humanities", an invited talk by Steffen Eger of Bielefeld University. The talk is part of OFAI's 2022 Lecture Series.
Members of the public are cordially invited to attend the talk via Zoom on Wednesday, 7 September 2022 at 18:30 CEST:
URL: https://us06web.zoom.us/j/84282442460?pwd=NHVhQnJXOVdZTWtNcWNRQllaQWFnQT09
Meeting ID: 842 8244 2460
Passcode: 678868
Talk abstract: In this talk, I will discuss our current work in the context of deep learning based text generation for the humanities. In particular, I will talk about (i) style-conditioned poetry generation, (ii) abstract-to-title generation (considering humorousness as one generation criterion), and (iii) cross-lingual cross-temporal summarization where the goal is to summarize a historical document in another modern language. Time permitting, I will also talk about evaluation metrics for text generation systems.
Speaker biography: Steffen Eger is currently stand-in professor at Bielefeld University. Previously, he was a PostDoc and group leader at TU Darmstadt and a PostDoc at Goethe University, Frankfurt. He holds a prestigious Heisenberg grant from the German Research Foundation (DFG). His research interests are natural language processing (NLP) and in particular evaluation metrics for text generation systems as well as topics at the intersection of NLP, the computational social sciences and the digital humanities.
