Controllable Multi-Character Psychology-Oriented Story Generation

TL;DR

This paper introduces a novel model called SoCP for story generation that considers multi-character emotional lines based on psychological theories, enabling richer emotional dynamics and better psychological state control in stories.

Contribution

It is the first to focus on characters' emotional lines in story generation and proposes a new attention mechanism for this purpose.

Findings

Generated stories accurately reflect characters' psychological states.

The model outperforms baselines in emotional consistency.

A new evaluation metric for psychological state control is effective.

Abstract

Story generation, which aims to generate a long and coherent story automatically based on the title or an input sentence, is an important research area in the field of natural language generation. There is relatively little work on story generation with appointed emotions. Most existing works focus on using only one specific emotion to control the generation of a whole story and ignore the emotional changes in the characters in the course of the story. In our work, we aim to design an emotional line for each character that considers multiple emotions common in psychological theories, with the goal of generating stories with richer emotional changes in the characters. To the best of our knowledge, this work is first to focuses on characters' emotional lines in story generation. We present a novel model-based attention mechanism that we call SoCP (Storytelling of multi-Character Psychology). We show that the proposed model can generate stories considering the changes in the psychological state of different characters. To take into account the particularity of the model, in addition to commonly used evaluation indicators(BLEU, ROUGE, etc.), we introduce the accuracy rate of psychological state control as a novel evaluation metric. The new indicator reflects the effect of the model on the psychological state control of story characters. Experiments show that with SoCP, the generated stories follow the psychological state for each character according to both automatic and human evaluations.