Creative language—the sort found in novels, film, and comics—contains a wide range of linguistic phenomena, from increased syntactic complexity (e.g., metaphors, sarcasm) to high-level discourse structures such as narrative and character arcs. In this talk, I present neural architectures for two different tasks involving creative language: 1) modeling dynamic fictional relationships in novels and 2) predicting dialogue and artwork from comic book panels. While creative language understanding has many applications (e.g., designing more engaging conversational agents), I motivate these tasks through quiz bowl, which is a trivia game that contains many questions about novels, paintings, and comics. I conclude by discussing work in progress on using the proposed models to improve quiz bowl question answering.
Mohit Iyyer is a fifth year Ph.D. student in the Department of Computer Science at the University of Maryland, College Park. He is also a member of the Computational Linguistics and Information Processing Lab and UMIACS. Along with his advisors, Jordan Boyd-Graber and Hal Daumé III, he works on problems that lie at the intersection of machine learning and natural language processing. His main research interest is in designing deep neural networks for both traditional NLP tasks (e.g., question answering, sentiment analysis) and new problems that involve understanding creative language.