Sequence-to-Sequence Language Models for Character and Emotion Detection in Dream Narratives
This work addresses the need for efficient quantitative analysis in dream research, though it is incremental as it applies existing methods to a new domain.
The authors tackled the problem of automating labor-intensive manual annotation of dream narratives by developing a sequence-to-sequence language model for character and emotion detection in the DreamBank corpus, achieving better performance with 28 times fewer parameters compared to a large language model using in-context learning.
The study of dreams has been central to understanding human (un)consciousness, cognition, and culture for centuries. Analyzing dreams quantitatively depends on labor-intensive, manual annotation of dream narratives. We automate this process through a natural language sequence-to-sequence generation framework. This paper presents the first study on character and emotion detection in the English portion of the open DreamBank corpus of dream narratives. Our results show that language models can effectively address this complex task. To get insight into prediction performance, we evaluate the impact of model size, prediction order of characters, and the consideration of proper names and character traits. We compare our approach with a large language model using in-context learning. Our supervised models perform better while having 28 times fewer parameters. Our model and its generated annotations are made publicly available.