Optimal Shift-Reduce Constituent Parsing with Structured Perceptron

Optimal Shift-Reduce Constituent Parsing with Structured Perceptron
复制标题

DOI:
10.3115/v1/p15-1148
复制
发表时间:
2015-07
期刊:
--
影响因子:
--
通讯作者:
Le Quang Thang;Hiroshi Noji;Yusuke Miyao
Le Quang Thang;Hiroshi Noji;Yusuke Miyao
中科院分区:
其他
文献类型:
--
作者:
Le Quang Thang;Hiroshi Noji;Yusuke Miyao

文献摘要

相似文献

我们提出了一个具有结构化感知器的成分移位-减少解析器,该解析器可以在实际运行时找到最佳解析。关键思想是促进动态规划和A*搜索的状态合并的新特征模板。我们的系统在标准英文实验中达到了91.1 F1,这是其他基于光束的系统即使在大光束尺寸下也无法达到的水平
We present a constituent shift-reduce parser with a structured perceptron that finds the optimal parse in a practical runtime. The key ideas are new feature templates that facilitate state merging of dynamic programming and A* search. Our system achieves 91.1 F1 on a standard English experiment, a level which cannot be reached by other beam-based systems even with large beam sizes.1