An Ion Exchange Mechanism Inspired Story Ending Generator for Different Characters
This addresses the need for personalized story generation in NLP applications, though it is incremental by focusing on character-specific endings rather than a broader paradigm shift.
The paper tackles the problem of generating story endings that vary by character, proposing a Character-oriented Story Ending Generator (CoSEG) that models character personalities and uses an ion exchange-inspired mechanism for interactions, achieving significant improvements in ending quality over state-of-the-art methods.
Story ending generation aims at generating reasonable endings for a given story context. Most existing studies in this area focus on generating coherent or diversified story endings, while they ignore that different characters may lead to different endings for a given story. In this paper, we propose a Character-oriented Story Ending Generator (CoSEG) to customize an ending for each character in a story. Specifically, we first propose a character modeling module to learn the personalities of characters from their descriptive experiences extracted from the story context. Then, inspired by the ion exchange mechanism in chemical reactions, we design a novel vector breaking/forming module to learn the intrinsic interactions between each character and the corresponding context through an analogical information exchange procedure. Finally, we leverage the attention mechanism to learn effective character-specific interactions and feed each interaction into a decoder to generate character-orient endings. Extensive experimental results and case studies demonstrate that CoSEG achieves significant improvements in the quality of generated endings compared with state-of-the-art methods, and it effectively customizes the endings for different characters.