首页> 外文期刊>IEEE transactions on audio, speech and language processing >Semantic Role Labeling Using a Grammar-Driven Convolution Tree Kernel
【24h】

Semantic Role Labeling Using a Grammar-Driven Convolution Tree Kernel

机译:使用语法驱动的卷积树内核的语义角色标记

获取原文
获取原文并翻译 | 示例

摘要

Convolution tree kernel has shown promising results in semantic role labeling (SRL). However, this kernel does not consider much linguistic knowledge in kernel design and only performs hard matching between subtrees. To overcome these constraints, this paper proposes a grammar-driven convolution tree kernel for SRL by introducing more linguistic knowledge. Compared with the standard convolution tree kernel, the proposed grammar-driven kernel has two advantages: 1) grammar-driven approximate substructure matching, and 2) grammar-driven approximate tree node matching. The two approximate matching mechanisms enable the proposed kernel to better explore linguistically motivated structured knowledge. Experiments on the CoNLL-2005 SRL shared task and the PropBank I corpus show that the proposed kernel outperforms the standard convolution tree kernel significantly. Moreover, we present a composite kernel to integrate a feature-based polynomial kernel and the proposed grammar-driven convolution tree kernel for SRL. Experimental results show that our composite kernel-based method significantly outperforms the previously best-reported ones.
机译:卷积树内核已在语义角色标记(SRL)中显示出令人鼓舞的结果。但是,此内核在内核设计中没有考虑太多的语言知识,仅在子树之间执行硬匹配。为了克服这些限制,本文通过引入更多的语言知识为SRL提出了一种语法驱动的卷积树内核。与标准卷积树内核相比,本文提出的语法驱动内核具有两个优点:1)语法驱动的近似子结构匹配,以及2)语法驱动的近似树节点匹配。两种近似匹配机制使所提出的内核能够更好地探索语言动机的结构化知识。在CoNLL-2005 SRL共享任务和PropBank I语料库上进行的实验表明,所提出的内核明显优于标准卷积树内核。此外,我们提出了一个复合内核,用于集成基于特征的多项式内核和所建议的文法驱动的卷积树内核。实验结果表明,我们的基于核的复合方法明显优于以前最佳报告的方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号