arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.05604cs.CLcs.LG
收藏

神经元CRF的势函数设计研究

An Investigation of Potential Function Designs for Neural CRF

ShanghaiTech University(上海科技大学);Shanghai Engineering Research Center of Intelligent Vision and Imaging(上海智能视觉与成像工程技术研究中心);Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences(中国科学院上海微系统与信息技术研究所);University of Chinese Academy of Sciences(中国科学院大学);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)

Zechuan Hu, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

摘要:

神经线性链CRF模型是序列标记中应用最广泛的方法之一。在本文中,我们研究了一系列越来越有表现力的潜在功能的神经CRF模型,它不仅集成了发射和转换功能,但也明确地把上下文单词的表示作为输入。我们广泛的实验表明,分解的四线性势函数的基础上的两个相邻的标签和两个相邻的词的矢量表示一致地达到最佳性能。

英文摘要:

The neural linear-chain CRF model is one of the most widely-used approach to sequence labeling. In this paper, we investigate a series of increasingly expressive potential functions for neural CRF models, which not only integrate the emission and transition functions, but also explicitly take the representations of the contextual words as input. Our extensive experiments show that the decomposed quadrilinear potential function based on the vector representations of two neighboring labels and two neighboring words consistently achieves the best performance.

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。

↑