论文标题
对神经CRF潜在功能设计的研究
An Investigation of Potential Function Designs for Neural CRF
论文作者
论文摘要
神经线性链CRF模型是序列标记最广泛使用的方法之一。在本文中，我们研究了神经CRF模型的一系列日益表达的潜在功能，这些功能不仅整合了发射和过渡函数，而且还明确地将上下文单词的表示形式视为输入。我们的广泛实验表明，基于两个相邻标签和两个相邻单词的向量表示，分解的四联势函数始终达到最佳性能。
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.
