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
中科院分区:
文献类型:
--
作者:
Le Quang Thang;Hiroshi Noji;Yusuke Miyao
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