arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.13298cs.CL

DiffusionNER:用于命名实体识别的边界扩散

DiffusionNER: Boundary Diffusion for Named Entity Recognition

Zhejiang University(浙江大学);Microsoft Research Asia(微软亚洲研究院)

Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, Yueting Zhuang

AI总结:

本文提出DiffusionNER,将命名实体识别建模为边界去噪扩散过程,通过前向加噪与反向去噪实现实体生成,在多个数据集上取得优于或可比的性能。

摘要:

在本文中,我们提出了DiffusionNER,它将命名实体识别任务建模为边界去噪扩散过程,从而从噪声跨度生成命名实体。在训练期间,DiffusionNER通过固定的前向扩散过程逐渐向黄金实体边界添加噪声,并学习反向扩散过程来恢复实体边界。在推理时,DiffusionNER首先从标准高斯分布中随机采样一些噪声跨度,然后通过学习到的反向扩散过程对其进行去噪来生成命名实体。提出的边界去噪扩散过程允许实体的渐进细化和动态采样,赋予DiffusionNER高效且灵活的实体生成能力。在多个平面和嵌套NER数据集上的实验表明,DiffusionNER取得了与先前最先进模型相当甚至更好的性能。

英文摘要:

In this paper, we propose DiffusionNER, which formulates the named entity recognition task as a boundary-denoising diffusion process and thus generates named entities from noisy spans. During training, DiffusionNER gradually adds noises to the golden entity boundaries by a fixed forward diffusion process and learns a reverse diffusion process to recover the entity boundaries. In inference, DiffusionNER first randomly samples some noisy spans from a standard Gaussian distribution and then generates the named entities by denoising them with the learned reverse diffusion process. The proposed boundary-denoising diffusion process allows progressive refinement and dynamic sampling of entities, empowering DiffusionNER with efficient and flexible entity generation capability. Experiments on multiple flat and nested NER datasets demonstrate that DiffusionNER achieves comparable or even better performance than previous state-of-the-art models.

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。

↑