Modeling Human Mental States with an Entity-based Narrative Graph. (arXiv:2104.07079v1 [cs.CL])

Understanding narrative text requires capturing characters’ motivations,
goals, and mental states. This paper proposes an Entity-based Narrative Graph
(ENG) to model the internal-states of characters in a story. We explicitly
model entities, their interactions and the context in which they appear, and
learn rich representations for them. We experiment with different task-adaptive
pre-training objectives, in-domain training, and symbolic inference to capture
dependencies between different decisions in the output space. We evaluate our
model on two narrative understanding tasks: predicting character mental states,
and desire fulfillment, and conduct a qualitative analysis.