arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.02333cs.CL
收藏

基于注意关系网络的槽标记少样本学习

Few-shot Learning for Slot Tagging with Attentive Relational Network

German Research Center for Artificial Intelligence(德国人工智能研究中心);University of Stuttgart(斯图加特大学)

Cennet Oguz, Ngoc Thang Vu

摘要:

基于度量的学习是用于少样本学习的众所周知的方法族,特别是在计算机视觉中。最近,它们已被用于许多自然语言处理应用程序,但不是槽标记。在本文中,我们探讨了基于度量的学习方法在槽标记任务,并提出了一种新的基于度量的学习架构-注意关系网络。我们提出的方法扩展了关系网络,使它们更适合自然语言处理应用程序一般,通过利用预训练的上下文嵌入,如ELMO和BERT,并通过使用注意力机制。SNIPS数据的结果表明,我们提出的方法优于其他国家的最先进的基于度量的学习方法。

英文摘要:

Metric-based learning is a well-known family of methods for few-shot learning, especially in computer vision. Recently, they have been used in many natural language processing applications but not for slot tagging. In this paper, we explore metric-based learning methods in the slot tagging task and propose a novel metric-based learning architecture - Attentive Relational Network. Our proposed method extends relation networks, making them more suitable for natural language processing applications in general, by leveraging pretrained contextual embeddings such as ELMO and BERT and by using attention mechanism. The results on SNIPS data show that our proposed method outperforms other state-of-the-art metric-based learning methods.

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。

↑