EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attention
This work addresses the problem of improving story generation for applications like creative writing or dialogue systems, but it appears incremental as it builds on existing neural methods with a specific enhancement.
The paper tackles the challenge of generating long narratives that maintain fluency, relevance, and coherence in automatic story generation by proposing EtriCA, a neural model that uses cross-attention to map context features to event sequences, resulting in significant outperformance over state-of-the-art baselines in evaluations.
One of the key challenges of automatic story generation is how to generate a long narrative that can maintain fluency, relevance, and coherence. Despite recent progress, current story generation systems still face the challenge of how to effectively capture contextual and event features, which has a profound impact on a model's generation performance. To address these challenges, we present EtriCA, a novel neural generation model, which improves the relevance and coherence of the generated stories through residually mapping context features to event sequences with a cross-attention mechanism. Such a feature capturing mechanism allows our model to better exploit the logical relatedness between events when generating stories. Extensive experiments based on both automatic and human evaluations show that our model significantly outperforms state-of-the-art baselines, demonstrating the effectiveness of our model in leveraging context and event features.