University of Maryland
Title: “Using Deep Learning to Understand and Answer Questions about Creative Language”
Abstract: Creative language—the sort found in novels, film, and comics—contains a wide range of linguistic phenomena, from phrasal and sentential syntactic complexity to high-level discourse structures such as narrative and character arcs. In this talk, Mohit will explore how we can use deep learning to understand, generate, and answer questions about creative language. He will begin by presenting deep neural network models for two tasks involving creative language understanding: 1) modeling dynamic relationships between fictional characters in novels, for which our models achieve higher interpretability and accuracy than existing work; and 2) predicting dialogue and artwork from comic book panels, in which we demonstrate that even state-of-the-art deep models struggle on problems that require commonsense reasoning. Next, he will introduce deep models that outperform all but the best human players on quiz bowl, a trivia game that contains many questions about creative language. Shifting to ongoing work, he will describe a neural language generation method that disentangles the content of a novel (i.e., the information or story it conveys) from the style in which it is written. Finally, he will conclude by integrating his work on deep learning, creative language, and question answering into a future research plan to build conversational agents that are both engaging and useful.
A reception will be held at 3:40 P.M. in the atrium outside the presentation room.