The cognitive brown bag speaker on Wednesday, March 20 will be Mohit Iyyer of UMass Computer Science (https://people.cs.umass.edu/~miyyer/). Title and abstract are below. As always, the talk is in Tobin 521B at 12:00. All are welcome.
Title: Towards Understanding Narratives with Artificial Intelligence
One of the fundamental goals of artificial intelligence is to build computers that understand language at a human level. Recent progress towards this goal has been fueled by deep learning, which represents words, sentences, and even documents with learned vectors of real-valued numbers. However, creative language—the sort found in novels, film, and comics—poses an immense challenge for such models because it 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, I discuss our recent work on applying deep learning to creative language understanding, as well as exploring the challenges that must be solved before further progress can be made. I begin with an general overview of deep learning before presenting model architectures for two tasks involving creative language understanding: 1) modeling dynamic relationships between fictional characters in novels, and 2) predicting dialogue and artwork from comic book panels. For both tasks, our models only achieve a surface-level understanding, limited by a lack of world knowledge, an inability to perform commonsense reasoning, and a reliance on huge amounts of data. I conclude by proposing ideas on how to push these models to produce deeper insights from creative language that might be of use to humanities researchers.