Parsing as Language Modeling

Parsing as Language Modeling
复制标题

DOI:
10.18653/v1/d16-1257
复制
发表时间:
2016-11
期刊:
--
影响因子:
--
通讯作者:
Do Kook Choe;Eugene Charniak
Do Kook Choe;Eugene Charniak
中科院分区:
其他
文献类型:
--
作者:
Do Kook Choe;Eugene Charniak

文献摘要

被引文献

相似文献

我们将句法解析重新定义为语言建模问题,并使用神经网络语言建模的最新进展来实现选区Penn Treebank解析的新技术水平-第23节的93.8 F 1,使用2-21作为训练,24作为开发,加上三训练。当树转换为斯坦福大学依赖关系时,UAS和LAS分别为95.9%和94.1%。
We recast syntactic parsing as a language modeling problem and use recent advances in neural network language modeling to achieve a new state of the art for constituency Penn Treebank parsing — 93.8 F 1 on section 23, us-ing 2-21 as training, 24 as development, plus tri-training. When trees are converted to Stanford dependencies, UAS and LAS are 95.9% and 94.1%.