LAUSR

Stories are useful tools with which we can exchange experience learnt in social contexts, ways to communicate futures in strategic planning, and unique building blocks that connect meanings in a movie or a virtual environment. Evolutionary computation (EC) techniques have the potential to overcome existing limitations in automated storytelling, whereby evolution can provide a process of innovation. However, one source of complexity lies in the transformation of a story in a natural language into a representation that EC can evolve easily. Another complexity arises from the fact that the ultimate judge for the quality of a story is a human being, and humans are diverse in their taste. This paper attempts to tackle the above complexities through an automatic story narration application. We present a methodology which can transform a story written in English into an event-level and hierarchical-level grammar using a network representation. This approach makes it possible to devise an encoding scheme that translates a story narration with flashback into a chromosome and vice versa. We then discuss different metrics for the evolutionary narration problem and use 42 human participants to evaluate the generated narrations. To incorporate diversified human opinions, we propose to build individual human-surrogate models from the human-evaluation experiment and further fuse them into an ensemble. The ensembles of human surrogate models serve as the objective functions of multi-objective EC to guide the generation of desirable stories from human perspectives. We demonstrate that this approach is successful in evolving better narrations as assessed by 31 human participants.