Gated Recursive Neural Network for Chinese Word Segmentation
Gated Recursive Neural Network for Chinese Word Segmentation
复制标题
DOI：
10.3115/v1/p15-1168
复制
发表时间：
2015-07
期刊：
影响因子：
--
通讯作者：
Xinchi Chen;Xipeng Qiu;Chenxi Zhu;Xuanjing Huang
中科院分区：
文献类型：
--
作者：
Xinchi Chen;Xipeng Qiu;Chenxi Zhu;Xuanjing Huang
近年来，自然语言处理任务的神经网络模型因其减轻人工特征工程负担的能力而受到越来越多的关注。然而，以前的神经模型无法像传统的离散特征方法那样提取复杂的特征组合。在本文中，我们提出了一个门控递归神经网络（GRNN）的中文分词，它包含重置和更新门，以纳入复杂的组合的上下文字符。由于GRNN相对较深，我们还使用了监督式分层训练方法来避免梯度扩散问题。在基准数据集上的实验表明，我们的模型优于以前的神经网络模型以及最先进的方法。
Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability of alleviating the burden of manual feature engineering. However, the previous neural models cannot extract the complicated feature compositions as the traditional methods with discrete features. In this paper, we propose a gated recursive neural network (GRNN) for Chinese word segmentation, which contains reset and update gates to incorporate the complicated combinations of the context characters. Since GRNN is relative deep, we also use a supervised layer-wise training method to avoid the problem of gradient diffusion. Experiments on the benchmark datasets show that our model outperforms the previous neural network models as well as the state-of-the-art methods.