MELISSA ROEMMELE: Augmenting human creativity with automated text generation

ABOUT TALK
In this session, we'll discuss how artificial intelligence and natural language processing can be used to help people with creative writing. In the first part of the session, Dr. Roemmele will illustrate this endeavor with an example from her own recent research, which includes experimental evidence that people author more creative text when they observe automatically generated examples of related text. In the second part of the session, she will give a brief tutorial of how a text generation model for this application can be built using open-source Python libraries.

ABOUT SPEAKER
Melissa Roemmele is a research scientist at RWS Language Weaver (Los Angeles, CA) working on interactive applications that use natural language processing to facilitate content understanding and creation. Her research passions center on the use of computers to analyze and augment human creativity in language and storytelling. She completed her PhD in 2018 in the Department of Computer Science at University of Southern California. During her PhD she worked at the USC Institute for Creative Technologies in the Narrative Group, which pursues research at the intersection of artificial intelligence and storytelling. Her dissertation explored machine learning approaches for interactively predicting “what happens next” in text-based stories, with a particular focus on the application of human authoring support.
GitHub: https://github.com/roemmele/
LinkedIn: https://www.linkedin.com/in/mroemmele/
Twitter: https://twitter.com/melissa_roem