Globally Normalized Transition-Based Neural Networks
Globally Normalized Transition-Based Neural Networks
复制标题
DOI：
10.18653/v1/p16-1231
复制
发表时间：
2016-03
期刊：
影响因子：
--
通讯作者：
D. Andor;Chris Alberti;David Weiss;Aliaksei Severyn;Alessandro Presta;Kuzman Ganchev;Slav Petrov
中科院分区：
文献类型：
--
作者：
D. Andor;Chris Alberti;David Weiss;Aliaksei Severyn;Alessandro Presta;Kuzman Ganchev;Slav Petrov
我们提出了一种全局归一化的基于变迁的神经网络模型，实现了最先进的词性标注、依存句法分析和句子压缩结果。我们的模型是一个简单的前馈神经网络，它运行在特定于任务的转换系统上，但获得了与递归模型相当或更高的精度。我们讨论了全局归一化相对于局部归一化的重要性：一个关键的见解是，标签偏差问题意味着全局归一化模型可以严格地比局部归一化模型更具表现力。
We introduce a globally normalized transition-based neural network model that achieves state-of-the-art part-of-speech tagging, dependency parsing and sentence compression results. Our model is a simple feed-forward neural network that operates on a task-specific transition system, yet achieves comparable or better accuracies than recurrent models. We discuss the importance of global as opposed to local normalization: a key insight is that the label bias problem implies that globally normalized models can be strictly more expressive than locally normalized models.