Dear colleagues,

we are happy to announce a talk by Dr. Mark Finlayson (Knight Foundation School of Computing and Information Sciences (KFSCIS) at Florida International University (FIU)) about Computational Approaches to Understanding Narrative in our colloquium  "Computational Literary Studies" at University of Bielefeld on 30th of Janurary, 18:00 c.t. (GMT+1). The talk will be held online (with hybrid attendance) via Zoom.

Link to the Zoom-Meeting:

https://uni-bielefeld.zoom-x.de/j/67554437983?pwd=VHNOUzNWMEZYeUkxUDJkZ015TXdlQT09

Meeting-ID: 675 5443 7983

Passwort: 135077

Abstract: Different discourse types present their own special challenges across the spectrum of Natural Language Processing (NLP) techniques, for example, models that are trained or tuned for specific discourse types (e.g., wall street journal articles), to techniques that make certain assumptions about the texts in question (e.g., that everything described takes places “in the real world”). The narrative discourse type presents numerous interesting challenges for existing techniques, and also suggests novel NLP tasks specifically relevant to narrative.  I present a selection of recent progress in the FIU Cognition, Narrative, and Culture (Cognac) Laboratory on NLP as applied to narrative. First, a new approach to timeline extraction that significantly improve our ability to extract, organize, and characterize timelines of events. Second, significantly improved animacy and character detection, where the goal is to determine whether a referent is animate and is acting as a “character”. We see that this approach requires some narratological sophistication to be successful.  Third, new improvements in sub-event and event relationship detection on narrative texts that take advantage of certain important features of narrative discourse. Fourth, inference from text of narrative structures that were described by Vladimir Propp.  I illustrate various applications of this work, focusing in particular on efforts to detect and model disinformation in the online space.

Bio: Dr. Mark A. Finlayson is Eminent Scholar Chaired Associate Professor of Computer Science in the Knight Foundation School of Computing and Information Sciences (KFSCIS) at Florida International University (FIU).  His research intersects artificial intelligence, natural language processing, and cognitive science. He directs the FIU SCIS Cognition, Narrative, and Culture (Cognac) Laboratory whose members focus on advancing the science of narrative, including: understanding the relationship between cognition, narrative, and culture; developing new methods and techniques for investigating questions related to language and narrative; and endowing machines with the ability to understand and use narratives for a variety of applications. He received his Ph.D. from MIT in computer science in 2012 under the supervision of Patrick H. Winston. He also holds the M.S. in Electrical Engineering from MIT (2001) and B.S. in Electrical Engineering from the University of Michigan, Ann Arbor (1998). Dr. Finlayson served as a research scientist at the MIT Computer Science and Artificial Intelligence Laboratory for 2½ years before coming to FIU, and served as the KSCIS Interim Associate Director between Fall 2020 and Spring 2022. Dr. Finlayson is a recipient of an NSF CAREER Award (2018), an IBM Faculty Award (2019), and a DARPA Young Faculty Award (2021). He has also served as the Edison Fellow for AI at the U.S. Patent and Trademark Office from 2019 until the present. Dr. Finlayson received FIU’s university-wide Faculty Award for Excellence in Research and Creative Activities (2019), a university-wide Top Scholar Award for Teaching and Mentoring (2018), and departmental awards for Excellence in Service (2016), Teaching (2018), Fundamental Research (2019), and Mentoring (2021). His work has been funded by NSF, NIH, ONR, DARPA, DHS, and IBM.

Best regards,

Berenike Herrmann & Daniel Kababgi