2020/10/14 by Faeze Brahman, Snigdha Chaturvedi, Brahman, Faeze +1 · 1 voice · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.2010.06822
EMNLP 2020, update: Conference version of Weber et al. (2020) is cited
arxiv published 2020/10/14 · arxiv created 2020/10/20 · arxiv updated 2020/10/22
Emotions and their evolution play a central role in creating a captivating story. In this paper, we present the first study on modeling the emotional trajectory of the protagonist in neural storytelling. We design methods that generate stories that adhere to given story titles and desired emotion arcs for the protagonist. Our models include Emotion Supervision (EmoSup) and two Emotion-Reinforced (EmoRL) models. The EmoRL models use special rewards designed to regularize the story generation process through reinforcement learning. Our automatic and manual evaluations demonstrate that these models are significantly better at generating stories that follow the desired emotion arcs compared to baseline methods, without sacrificing story quality.