arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.12463cs.CLcs.AI
收藏

EtriCA:交叉注意增强的事件触发上下文感知故事生成

EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attention

The University of Surrey(萨里大学);The University of Sheffield(谢菲尔德大学);Beihang University(北京航空航天大学)

Chen Tang, Chenghua Lin, Henglin Huang, Frank Guerin, Zhihao Zhang

摘要:

自动故事生成的关键挑战之一是如何生成能够保持流畅性、相关性和连贯性的长篇叙述。尽管最近的进展,目前的故事生成系统仍然面临着如何有效地捕捉上下文和事件的功能,这对模型的生成性能有着深远的影响的挑战。为了解决这些挑战,我们提出了EtriCA,一种新的神经生成模型,它提高了相关性和连贯性的生成的故事,通过剩余的映射上下文功能的事件序列与交叉注意力机制。这样的特征捕获机制使我们的模型在生成故事时能够更好地利用事件之间的逻辑相关性。基于自动和人工评估的大量实验表明,我们的模型显著优于最先进的基线,证明了我们的模型在利用上下文和事件特征方面的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑