UMass Machine Learning and Friends Lunch | Main / Understanding And Answering Questions About Creative Language

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.