Sequence-to-Sequence Language Models for Character and Emotion Detection in Dream Narratives

arXiv:2403.15486v1 Announce Type: new
Abstract: 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 …

abstract annotation arxiv automate cognition consciousness cs.ai cs.cl culture detection dreams emotion emotion detection framework human labor language language models natural natural language paper process study through type understanding