arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.02181cs.CLcs.AIcs.LGstat.ML
收藏

自然语言处理中的注意力

Attention in Natural Language Processing

University of Bologna(博洛尼亚大学);University of Modena and Reggio Emilia(摩德纳和雷焦艾米利亚大学)

Andrea Galassi, Marco Lippi, Paolo Torroni

摘要:

注意力是一种越来越受欢迎的机制,广泛应用于各种神经结构中。该机制本身已经以各种形式实现。然而,由于这一领域的快速发展,仍然缺乏对注意力的系统概述。在这篇文章中,我们定义了一个统一的模型,在自然语言处理的注意力架构,重点是那些设计工作与文本数据的矢量表示。我们提出了一个分类的注意力模型,根据四个维度:表示的输入,兼容性函数,分布函数,和输入和/或输出的多重性。我们提出的例子,先验信息可以利用注意力模型和讨论正在进行的研究工作和开放的挑战,在这个令人兴奋的领域提供了大量的文献的第一个广泛的分类。

英文摘要:

Attention is an increasingly popular mechanism used in a wide range of neural architectures. The mechanism itself has been realized in a variety of formats. However, because of the fast-paced advances in this domain, a systematic overview of attention is still missing. In this article, we define a unified model for attention architectures in natural language processing, with a focus on those designed to work with vector representations of the textual data. We propose a taxonomy of attention models according to four dimensions: the representation of the input, the compatibility function, the distribution function, and the multiplicity of the input and/or output. We present the examples of how prior information can be exploited in attention models and discuss ongoing research efforts and open challenges in the area, providing the first extensive categorization of the vast body of literature in this exciting domain.

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。

↑