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 2305.17458cs.CL
收藏

一种用于事件骨架生成的扩散模型

A Diffusion Model for Event Skeleton Generation

Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));International Digital Economy Academy (IDEA)(国际数字经济研究院(IDEA))

Fangqi Zhu, Lin Zhang, Jun Gao, Bing Qin, Ruifeng Xu, Haiqin Yang

AI总结:

本文提出首个用于事件骨架生成的扩散模型DEGM,通过嵌入与舍入技术、自定义边损失及去噪训练,将离散事件图转化为可学习潜在表示并迭代纠错,在三个IED数据集上优于现有方法。

摘要:

事件骨架生成旨在从一组事件实例图中归纳出包含抽象事件节点及其时序关系的事件模式骨架图,是时序复杂事件模式归纳任务中的关键步骤。现有方法从图生成的角度有效解决了该任务,但对噪声敏感且存在误差累积问题,例如在生成模式时无法纠正错误。为此,我们提出了一种新颖的扩散事件图模型(DEGM)来解决这些问题。我们的DEGM是首个可用于事件骨架生成的扩散模型,其中引入了嵌入和舍入技术以及自定义的基于边的损失,将离散事件图转换为可学习的潜在表示。此外,我们提出了一种去噪训练过程以保持模型的鲁棒性。因此,DEGM推导出最终模式,通过在模式生成过程中迭代优化潜在表示来保证错误纠正。在三个IED爆炸数据集上的实验结果表明,我们的DEGM比其他最先进的基线方法取得了更好的结果。我们的代码和数据可在https://github.com/zhufq00/EventSkeletonGeneration获取。

英文摘要:

Event skeleton generation, aiming to induce an event schema skeleton graph with abstracted event nodes and their temporal relations from a set of event instance graphs, is a critical step in the temporal complex event schema induction task. Existing methods effectively address this task from a graph generation perspective but suffer from noise-sensitive and error accumulation, e.g., the inability to correct errors while generating schema. We, therefore, propose a novel Diffusion Event Graph Model~(DEGM) to address these issues. Our DEGM is the first workable diffusion model for event skeleton generation, where the embedding and rounding techniques with a custom edge-based loss are introduced to transform a discrete event graph into learnable latent representation. Furthermore, we propose a denoising training process to maintain the model's robustness. Consequently, DEGM derives the final schema, where error correction is guaranteed by iteratively refining the latent representation during the schema generation process. Experimental results on three IED bombing datasets demonstrate that our DEGM achieves better results than other state-of-the-art baselines. Our code and data are available at https://github.com/zhufq00/EventSkeletonGeneration.

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。

↑