Melissa Roemmele

Melissa Roemmele


Melissa Roemmele is a research scientist at SDL in Los Angeles, working on interactive applications that use NLP to facilitate content understanding and creation. She completed her PhD in 2018 in the Department of Computer Science at University of Southern California. There she worked at the USC Institute for Creative Technologies in the Narrative Group led by her advisor Andrew Gordon, which pursues research at the intersection of artificial intelligence and storytelling. Her thesis explored machine learning approaches for interactively predicting “what happens next” in text-based stories, both in a commonsense reasoning framework as well as for human authoring support.

The Curious Role of Language Generation in Automated Assistance for Story Writing

AI has long envisioned using computers to automatically write stories. While a lot of work focuses on systems that perform this task autonomously, another objective is for applications to collaborate with human authors in augmenting their story writing abilities. In this talk, I’ll discuss the foundations and challenges of automated assistance for story writing, focusing in particular on the issue of supporting creativity. Motivated by observations from my own research on this endeavor, I’ll propose that it requires a different paradigm from that of other generation tasks, one that centers on the goals of the human author.